DETAILED ACTION
Notice of AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/20/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-8, 11-18 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The Independent claim 1 recites “extracting from an inbound audio signal for an inbound speaker, by a computer, a feature vector for one or more acoustic features”; “generating, by the computer, one or more quality measures and an overall quality measure for the inbound audio signal, by executing a machine-learning architecture using as input the feature vector for the one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal”; “generating, by the computer, a final similarity score for verifying the inbound speaker by combining an initial similarity score with the one or more quality measures or the overall quality measure”; “and verifying, by the computer, the inbound speaker as an enrolled speaker based upon comparing the final similarity score against a verification threshold”. The limitations above as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process, as this could be performed in the human mind or with the aid of pen and paper.
The limitation of "extracting ... ", "generating ... ", "verifying ... ", as drafted covers mental activities. More specifically, a person can listen to a speech from a speaker, can determine an acoustic feature such as loudness or duration, can generate quality measures by using the acoustic features, where quality measure can be a similarity between the expected quality descriptor ( such as duration of speech) and the quality descriptor of the speaker, generating/calculating a final similarity score by combining initial similarity score and quality measures and verifying the speaker as an enrolled speaker by comparing the final score with a predetermined threshold. The above steps, as drafted, is a process that under its broadest reasonable interpretation, covers performance of the limitation in the mind. There is, nothing in the claim element precludes the step from practically being performed in the human mind. Additionally, the mere nominal recitation of a generic computer appliance does not take the claim limitation out of the mental processes grouping. Thus, the claim recites a mental process.
The claim recites the additional limitation of “machine-learning architecture”, for performing the method, which is recited at a high level of generality and are recited as performing generic computer functions routinely used in computer applications. The current specification in paragraph [0023] specifies “the machine-learning architectures may include any number and combination of machine-learning techniques or types of machine-learning structures, such as neural network architectures and Gaussian Mixture Models (GMMs), among others”, which is generic and not sufficient to amount to significantly more than the judicial exception. This is no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
Thus, taken alone, the additional element does not amount to significantly more than the above identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds
nothing that is not already present when looking at the elements taken individually. There is no indication
that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation. Claim 1 is therefore not drawn to eligible subject matter as this is directed to an abstract idea without
significantly more than the abstract idea.
The Independent claim 11 recites “a database configured store an enrolled voiceprint for an enrolled speaker”; “and a server comprising a processor configured to: generate one or more quality measures and an overall quality measure for an inbound audio signal, by executing a machine-learning architecture using as input a feature vector for one or more acoustic features”, “the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal”; “generate a final similarity score for verifying the inbound speaker by combining an initial similarity score with the one or more quality measures or the overall quality measure”; “and verify the inbound speaker as an enrolled speaker based upon comparing the final similarity score against a verification threshold”. The limitations above as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process, as this could be performed in the human mind or with the aid of pen and paper.
The limitation of "store ... ", "generate ... ", "verify ... ", as drafted covers mental activities. More specifically, a person can write down some characteristics of a speaker corresponding to that speaker, can listen to a speech from a speaker, can determine an acoustic feature such as loudness or duration, can generate quality measures by using the acoustic features, where quality measure can be a similarity between the expected quality descriptor ( such as duration of speech) and the quality descriptor of the speaker, generating/calculating a final similarity score by combining initial similarity score and quality measures and verifying the speaker as an enrolled speaker by comparing the final score with a predetermined threshold. The above steps, as drafted, is a process that under its broadest reasonable interpretation, covers performance of the limitation in the mind. There is, nothing in the claim element precludes the step from practically being performed in the human mind. Additionally, the mere nominal recitation of a generic computer appliance does not take the claim limitation out of the mental processes grouping. Thus, the claim recites a mental process.
The claim recites the additional limitations of “ server’, “processor”, “machine-learning architecture”, for performing the method, which are recited at a high level of generality and are recited as performing generic computer functions routinely used in computer applications. The current specification in paragraph [0023] specifies “the machine-learning architectures may include any number and combination of machine-learning techniques or types of machine-learning structures, such as neural network architectures and Gaussian Mixture Models (GMMs), among others”, which is generic and not sufficient to amount to significantly more than the judicial exception. This is no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Thus, taken alone, the additional elements do not amount to significantly more than the above identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds
nothing that is not already present when looking at the elements taken individually. There is no indication
that the combination of elements improve the functioning of a computer or improve any other technology. Their collective functions merely provide conventional computer implementation. Claim 11 is therefore not drawn to eligible subject matter as this is directed to an abstract idea without significantly more than the abstract idea.
Claims 2, 12 recite “generating, by the computer, the initial similarity score by executing a second machine-learning architecture using as input an inbound speaker embedding and an enrolled voiceprint for the enrolled speaker”, to determine an initial similarity score by using than acoustic feature vector of the speaker and the characteristics of voice print, could be performed with the aid of pen and paper. The claims recite additional limitations of “processor”, “ machine-learning architecture”, which are recited in the specification as performing generic computer functions, which are not sufficient to amount to significantly more than the judicial exception. The claims 2, 12 as drafted, are not patent eligible.
Claims 3, 13 recite “generating, by the computer, the enrolled voiceprint by combining a plurality of enrollee embeddings”, the voiceprint or voice characteristics of a speaker could be generated by combing multiple vector features by the enrolled speaker, which could be performed with the aid of pen and paper. The claims recite additional limitations of “processor”, which is recited in the specification as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 3, 13 as drafted, are not patent eligible.
Claims 4, 14 recite “generating, by the computer, the plurality of enrollee embeddings by executing the second machine-learning architecture using as input a plurality of enrollee audio samples, wherein the inbound speaker embedding is generated by executing the second machine-learning architecture using as input the feature vector for the one or more acoustic features of the inbound audio signal”, a plurality of speaker embeddings or vectors can be generated from the input feature vector of the acoustic feature of a speaker and could be performed with the aid of pen and paper. The claims recite additional limitations of “processor”, “ machine-learning architecture”, which are recited in the specification as performing generic computer functions, which are not sufficient to amount to significantly more than the judicial exception. The claims 4, 14 as drafted, are not patent eligible.
Claims 5, 15 recite “generating the one or more quality measures for the inbound audio signal includes generating, by the computer, the overall quality measure based upon each of the quality measures”, an overall quality measures could be generated by generating each quality measure of an audio signal, such as speech and which could be performed with the aid of pen and paper. The claims recite additional limitations of “processor”, which is recited in the specification as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 5, 15 as drafted, are not patent eligible.
Claims 6, 16 recite “generating the one or more quality measures includes: generating, by the computer, a plurality of speech segments from the inbound audio signal; and determining, by the computer, a total duration of speech based upon the plurality of speech segments”, quality measure can include total duration of speech in multiple speech segment, which is an evaluation, observation and could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitations of “processor”, which is recited in the specification as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 6, 16 as drafted, are not patent eligible.
Claims 7, 17 recite “generating a quality measure includes determining, by the computer, a level of similarity between an inbound speaker embedding and a corresponding enrolled speaker embedding for an enrolled audio signal”, quality measure can be a similarity between an inbound speaker vector and an enrolled or saved speaker vector, which could be an evaluation, observation, could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitations of “processor”, which is recited in the specification as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 7, 17 as drafted, are not patent eligible.
Claims 8, 18 recite “receiving, by the computer, one or more clean enrollment audio signals for the enrolled speaker; generating, by the computer, one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation; and extracting, by the computer, one or more enrolled quality embeddings for the enrolled speaker by applying a second machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals”, a person can identify a quality measure or vector from a clean audio signal and a noisy signal, which is an evaluation, observation and could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitations of “processor”, “ machine-learning architecture”, which are recited in the specification as performing generic computer functions, which are not sufficient to amount to significantly more than the judicial exception. The claims 8, 18 as drafted, are not patent eligible.
Double Patenting
The non-statutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A non-statutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on non-statutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a non-statutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based e-Terminal Disclaimer may be filled out completely online using web-screens. An e-Terminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about e-Terminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1, 2, 5-8, 11, 12 and 15-18 are rejected on the ground of non-statutory double patenting as being unpatentable over claims 1, 3, 4, 7-9, and 11-14 of U.S. Patent No. 12,190,905. Although the claims at issue are not identical, they are not patentably distinct from each other because claims 1, 2, 5-8, 11, 12 and 15-18 of the instant application similar in scope and content of the patented claims 1, 3, 4, 7-9, and 11-14 of the patent issued to the same Applicant.
It is clear that all the elements of the application claims 1, 2, 5-8, 11, 12 and 15-18 are to be found in patented claims 1, 3, 4, 7-9, and 11-14 (as the application claims 1, 2, 5-8, 11, 12 and 15-18 fully encompasses patented claims 1, 3, 4, 7-9, and 11-14). The difference between the application claims and the patent claims lies in the fact that the patented claims includes many more elements and are thus much more specific. Thus the invention of claims 1, 3, 4, 7-9, and 11-14 of the patent is in effect a “species” of the “generic” invention of the application claims 1, 2, 5-8, 11, 12 and 15-18. It has been held that the generic invention is “anticipated” by the “species”. See In re Goodman, 29 USPQ2d 2010 (Fed. Cir. 1993). Since application claims 1, 2, 5-8, 11, 12 and 15-18 are anticipated by claims 1, 3, 4, 7-9, and 11-14 of the patent, it is not patentably distinct from of the patented claims.
Application No: 18/989,690
Patent No: 12,190,905
1. A computer-implemented method comprising:
extracting from an inbound audio signal for an inbound speaker, by a computer, a feature vector for one or more acoustic features;
generating, by the computer, one or more quality measures and an overall quality measure for the inbound audio signal, by executing a machine-learning architecture using as input the feature vector for the one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal;
generating, by the computer, a final similarity score for verifying the inbound speaker by combining an initial similarity score with the one or more quality measures or the overall quality measure;
and verifying, by the computer, the inbound speaker as an enrolled speaker based upon comparing the final similarity score against a verification threshold.
1. A computer-implemented method comprising:
extracting from an inbound audio signal for an inbound speaker, by a computer, a feature vector for one or more acoustic features;
generating, by the computer, one or more quality measures and an overall quality measure for the inbound audio signal, by applying a first machine-learning architecture to the feature vector for the one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for the call audio of the inbound audio signal;
extracting, by the computer, an inbound speaker embedding for the inbound speaker from the one or more acoustic features for the inbound audio signal, by applying a second machine- learning architecture to the feature vector for the one or more acoustic features of the inbound audio signal;
generating, by the computer, a first similarity score for the inbound speaker based upon the inbound speaker embedding and an enrolled voiceprint for an enrolled speaker, by applying the second machine-learning architecture;
generating, by the computer, a second similarity score for verifying the inbound speaker, the second similarity score generated based upon the one or more quality measures and the first similarity score;
and verifying, by the computer, the inbound speaker as the enrolled speaker based upon comparing the second similarity score against a verification threshold.
2. The method according to claim 1, further comprising generating, by the computer, the initial similarity score by executing a second machine-learning architecture using as input an inbound speaker embedding and an enrolled voiceprint for the enrolled speaker.
Claim 1
3. The method according to claim 2, further comprising generating, by the computer, the enrolled voiceprint by combining a plurality of enrollee embeddings.
4. The method according to claim 3, further comprising generating, by the computer, the plurality of enrollee embeddings by executing the second machine-learning architecture using as input a plurality of enrollee audio samples, wherein the inbound speaker embedding is generated by executing the second machine-learning architecture using as input the feature vector for the one or more acoustic features of the inbound audio signal.
5. The method according to claim 1, wherein generating the one or more quality measures for the inbound audio signal includes generating, by the computer, the overall quality measure based upon each of the quality measures.
3. The method according to claim 1, wherein generating the one or more quality measures for the inbound audio signal includes generating, by the computer, the overall quality measure based upon each of the quality measures.
6. The method according to claim 1, wherein generating the one or more quality measures includes: generating, by the computer, a plurality of speech segments from the inbound audio signal;
and determining, by the computer, a total duration of speech based upon the plurality of speech segments.
4. The method according to claim 1, wherein generating the one or more quality measures includes: generating, by the computer, a plurality of speech segments from the inbound audio signal;
and determining, by the computer, a total duration of speech based upon the plurality of speech segments.
7. The method according to claim 1, wherein generating a quality measure includes determining, by the computer, a level of similarity between an inbound speaker embedding and a corresponding enrolled speaker embedding for an enrolled audio signal.
7. The method according to claim 1, wherein generating a quality measure includes determining, by the computer, a similarity between the inbound speaker embedding and a corresponding enrolled speaker embedding for an enrolled audio signal, wherein the quality measure is based upon the similarity.
8. The method according to claim 1, further comprising: receiving, by the computer, one or more clean enrollment audio signals for the enrolled speaker; generating, by the computer, one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation; and extracting, by the computer, one or more enrolled quality embeddings for the enrolled speaker by applying a second machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals.
8. The method according to claim 1, further comprising: receiving, by the computer, one or more clean enrollment audio signals for the enrolled speaker; generating, by the computer, one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation; and extracting, by the computer, one or more enrolled quality embeddings for the enrolled speaker by applying the first machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals.
9. The method according to claim 8, further comprising enabling, by the computer, classification layers and loss layers of the second machine-learning architecture in a training phase of the second machine-learning architecture.
10. The method according to claim 8, further comprising disabling, by the computer, classification layers and loss layers of the second machine-learning architecture in a deployment phase of the second machine-learning architecture.
11. A system comprising:
a database configured store an enrolled voiceprint for an enrolled speaker;
and a server comprising a processor configured to:
generate one or more quality measures and an overall quality measure for an inbound audio signal, by executing a machine-learning architecture using as input a feature vector for one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal;
generate a final similarity score for verifying the inbound speaker by combining an initial similarity score with the one or more quality measures or the overall quality measure;
and verify the inbound speaker as an enrolled speaker based upon comparing the final similarity score against a verification threshold.
9. A system comprising:
a database configured store an enrolled voiceprint for an enrolled speaker;
and a server comprising a processor configured to: extract from an inbound audio signal for an inbound speaker a feature vector for one or more acoustic features;
generate one or more quality measures and an overall quality measure for the inbound audio signal, by applying a first machine-learning architecture to the feature vector for the one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for the call audio of the inbound audio signal;
extract an inbound speaker embedding for the inbound speaker from the one or more acoustic features for the inbound audio signal, by applying a second machine-learning architecture to the feature vector for the one or more acoustic features of the inbound audio signal;
generate a first similarity score for the inbound speaker based upon the inbound speaker embedding and the enrolled voiceprint for the enrolled speaker, by applying the second machine-learning architecture;
generate a second similarity score for verifying the inbound speaker, the second similarity score generated based upon the one or more quality measures and the first similarity score;
and verify the inbound speaker as the enrolled speaker based upon comparing the second similarity score against a verification threshold.
12. The system according to claim 11, wherein the processor is further configured to generate the initial similarity score by executing a second machine-learning architecture using as input an inbound speaker embedding and an enrolled voiceprint for the enrolled speaker.
Claim 9
13. The system according to claim 12, wherein the processor is further configured to generate the enrolled voiceprint by combining a plurality of enrollee embeddings.
14. The system according to claim 13, wherein the processor is further configured to generate the plurality of enrollee embeddings by executing the second machine-learning architecture using as input a plurality of enrollee audio samples, wherein the inbound speaker embedding is generated by executing the second machine-learning architecture using as input the feature vector for the one or more acoustic features of the inbound audio signal.
15. The system according to claim 11, wherein the processor is further configured to generate the one or more quality measures for the inbound audio signal by generating the overall quality measure based upon each of the quality measures.
11. The system according to claim 9, wherein when generating the one or more quality measures for the inbound audio signal, the server is further configured to generate the overall quality measure based upon each of the quality measures.
16. The system according to claim 11, wherein the processor is further configured to generate the one or more quality measures by: generating a plurality of speech segments from the inbound audio signal; and determining a total duration of speech based upon the plurality of speech segments.
12. The system according to claim 9, wherein when generating the one or more quality measures, the server is further configured to: generate a plurality of speech segments from the inbound audio signal; and determine a total duration of speech based upon the plurality of speech segments.
17. The system according to claim 11, wherein the processor is further configured to generate a quality measure by determining a level of similarity between an inbound speaker embedding and a corresponding enrolled speaker embedding for an enrolled audio signal.
13. The system according to claim 9, wherein when generating a quality measure the server is configured to: determine a similarity between the inbound speaker embedding and a corresponding enrolled speaker embedding for an enrolled audio signal, wherein the quality measure is based upon the similarity.
18. The system according to claim 11, wherein the processor is further configured to: receive one or more clean enrollment audio signals for the enrolled speaker; generate one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation; and extract one or more enrolled quality embeddings for the enrolled speaker by applying a second machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals.
14. The system according to claim 9, wherein the server is further configured to: receive one or more clean enrollment audio signals for the enrolled speaker; generate one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation; and extract one or more enrolled quality embeddings for the enrolled speaker by applying the first machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals.
19. The system according to claim 18, wherein the processor is further configured to enable classification layers and loss layers of the second machine-learning architecture in a training phase of the second machine-learning architecture.
20. The system according to claim 19, wherein the processor is further configured to disable the classification layers and loss layers of the second machine-learning architecture in a deployment phase of the second machine-learning architecture.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 5, 7, 11, 15 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Lesso et al. ( US 20190333522 A1), hereinafter referenced as Lesso, in view of Dong et al. (Us 20190124441 A1), hereinafter referenced as Dong.
Regarding Claim 1, Lesso teaches a computer-implemented method comprising:
extracting from an inbound audio signal for an inbound speaker, by a computer, a feature [vector] for one or more acoustic features ( Lesso: Para.[0336], Fig.13, the speaker validation module 204 receives audio input, comprising speech from input 202. The module 204 comprises a feature extraction module 214 which is configured to perform a feature extraction operation on the received audio);
generating, by the computer, a final similarity score for verifying the inbound speaker by combining an initial similarity score with the one or more quality measures or the overall quality measure (Lesso: Para.[0340],[0341], Fig.13, the speaker ID score 204a ( as final similarity score) is generated, which is used as an input to the decision gating module 208, by combining a series of stored speaker models 220 representing different enrolled speakers ( as initial similarity) and the sound classification 222 ( as quality measure) to a scoring or distance module 218. The scoring may comprise calculating a distance metric for the distance the speech of the received audio is from the speech of an enrolled speaker, a probability metric that the speech of the received audio is the speech of an enrolled speaker, or a log likelihood ratio that the speech of the received audio is that of an enrolled speaker) ;
and verifying, by the computer, the inbound speaker as an enrolled speaker based upon comparing the final similarity score against a verification threshold ( Lesso: Para.[0306], If the similarity score exceeds a particular threshold, meaning that the degree of similarity is high enough, then the received speech is considered to be that of the enrolled user. Para.[0368], Fig.15, The decision gating module 208 comprises a speaker validity check 232 which checks whether a speaker has been identified from the received audio from the output 204a of the speaker validity module 204, and further comprises an audio validity check 234 which checks whether the received audio is valid from the output 206a of the audio validity module 206. If both checks are passed, the decision gating module 208 comprises a power gating or fusion module 236, which is arranged to generate an output signal 208a to indicate the speaker validity).
Lesso while teaching the method according to claim 1, fails to explicitly teach the claimed, extracting from an inbound audio signal for an inbound speaker, by a computer, a feature vector for one or more acoustic features ; generating, by the computer, one or more quality measures and an overall quality measure for the inbound audio signal, by executing a machine-learning architecture using as input the feature vector for the one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal;
However, Dong does teach the claimed, extracting from an inbound audio signal for an inbound speaker, by a computer, a feature vector for one or more acoustic features ( Dong: Para.[0049], Fig.3, the acoustic quality determinator 221 extracts one or more features from the digital audio signal, obtains one or more acoustic feature vectors of a certain length),
generating, by the computer, one or more quality measures and an overall quality measure for the inbound audio signal, by executing a machine-learning architecture using as input the feature vector for the one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal ( Dong: Para.[0046]-[0050], Fig.3, the voice status determinator 220 in vocal analyzer 200 consists of an acoustic quality determinator 221 configured to determine an acoustic quality of the digital audio signal and a health status determinator 222 configured to classify a health status of a user. The acoustic quality determinator 221 extracts one or more features from the digital audio signal, obtains one or more acoustic feature vectors of a certain length, and inputs the one or more acoustic feature vectors and acoustic feature vectors of a target audio signal into the input layer of the first convolutional neural network model. The first convolutional neural network model calculates the degree of similarity between the digital audio signal and the target audio signal, and output the degree of similarity in terms of a tune, a pitch, a volume of the sound, from the fully connected layer ( quality measures). The health status determinator 222 is configured to classify a health status of a user. Thus, the voice status determinator 220 includes both acoustic quality and health status ( overall quality measure)) ;
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Dong’s teaching of a vocal training apparatus having a microphone and a vocal analyzer, a vocal training method , into the system and method of speaker identification by analyzing speech signals, taught by Lesso, because, by determining the acoustic quality of different user, a personalized data base for each user based on the identification information of the user can be established and user can be identified authentically. (Dong, Para.[0042]).
Regarding Claim 11, Lesso teaches a system comprising:
a database configured store an enrolled voiceprint for an enrolled speaker ( Lesso: Para.[0341], [0376], Figs. 13,16, speaker models 220 or 308, stores speech/voiceprint from the enrolled speakers to be used for speaker recognition) ;
and a server comprising a processor configured to ( Lesso : Para.[0240],[0244], Fig. 2, processor 16. Speech/speaker recognition system may be located on one or more remote server in a cloud computing environment):
generate a final similarity score for verifying the inbound speaker by combining an initial similarity score with the one or more quality measures or the overall quality measure (Lesso: Para.[0340],[0341], Fig.13, the speaker ID score 204a ( as final similarity score) is generated, which is used as an input to the decision gating module 208, by combining a series of stored speaker models 220 representing different enrolled speakers ( as initial similarity) and the sound classification 222 ( as quality measure) to a scoring or distance module 218. The scoring may comprise calculating a distance metric for the distance the speech of the received audio is from the speech of an enrolled speaker, a probability metric that the speech of the received audio is the speech of an enrolled speaker, or a log likelihood ratio that the speech of the received audio is that of an enrolled speaker) ;
and verify the inbound speaker as an enrolled speaker based upon comparing the final similarity score against a verification threshold ( Lesso: Para.[0306], If the similarity score exceeds a particular threshold, meaning that the degree of similarity is high enough, then the received speech is considered to be that of the enrolled user. Para.[0368], Fig.15, The decision gating module 208 comprises a speaker validity check 232 which checks whether a speaker has been identified from the received audio from the output 204a of the speaker validity module 204, and further comprises an audio validity check 234 which checks whether the received audio is valid from the output 206a of the audio validity module 206. If both checks are passed, the decision gating module 208 comprises a power gating or fusion module 236, which is arranged to generate an output signal 208a to indicate the speaker validity).
Lesso while teaching the system according to claim 11, fails to explicitly teach the claimed, generate one or more quality measures and an overall quality measure for an inbound audio signal, by executing a machine-learning architecture using as input a feature vector for one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal;
However, Dong does teach the claimed, generate one or more quality measures and an overall quality measure for an inbound audio signal, by executing a machine-learning architecture using as input a feature vector for one or more acoustic features, the one or more quality measures corresponding to a similarity between one or more expected quality descriptors and one or more quality descriptors for call audio of the inbound audio signal ( Dong: Para.[0046]-[0050], Fig.3, the voice status determinator 220 in vocal analyzer 200 consists of an acoustic quality determinator 221 configured to determine an acoustic quality of the digital audio signal and a health status determinator 222 configured to classify a health status of a user. The acoustic quality determinator 221 extracts one or more features from the digital audio signal, obtains one or more acoustic feature vectors of a certain length, and inputs the one or more acoustic feature vectors and acoustic feature vectors of a target audio signal into the input layer of the first convolutional neural network model. The first convolutional neural network model calculates the degree of similarity between the digital audio signal and the target audio signal, and output the degree of similarity in terms of a tune, a pitch, a volume of the sound, from the fully connected layer ( quality measures). The health status determinator 222 is configured to classify a health status of a user. Thus, the voice status determinator 220 includes both acoustic quality and health status ( overall quality measure)) ;
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Dong’s teaching of a vocal training apparatus having a microphone and a vocal analyzer, a vocal training method , into the system and method of speaker identification by analyzing speech signals, taught by Lesso, because, by determining the acoustic quality of different user, a personalized data base for each user based on the identification information of the user can be established and user can be identified authentically. (Dong, Para.[0042]).
Regarding Claim 5, Lesso in view of Dong teach the method according to claim 1. Dong further teaches, wherein generating the one or more quality measures for the inbound audio signal includes generating, by the computer, the overall quality measure based upon each of the quality measures ( Dong: Para.[0036],[0037], Fig.3, the vocal analyzer 200 is configured to determine an acoustic quality of the digital audio signal, configured to generate an acoustic quality determination signal, the acoustic quality refers to a degree of similarity between a note in a sound produced by the user in the vocal training and a target note, the degree of similarity in terms of a tune, a pitch, a volume of the sound. health status of the vocal organ include fatigue (e.g., fatigue of the vocal cord), overuse or misuse (e.g., overuse or misuse of the vocal cord), and pathological change ( e.g., pathological change of the throat). The acoustic quality and health status indication from indicator 130 is the overall quality which includes each quality measures).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Dong’s teaching of a vocal training apparatus having a microphone and a vocal analyzer, a vocal training method , into the system and method of speaker identification by analyzing speech signals, taught by Lesso, because, by determining the acoustic quality of different user, a personalized data base for each user based on the identification information of the user can be established and user can be identified authentically. (Dong, Para.[0042]).
Claim 15 is a system claim performing the steps in method claim 5 above and as such, claim 15 is similar in scope and content to claim 5 and therefore, claim 15 is rejected under similar rationale as presented against claim 5 above.
Regarding Claim 7, Lesso in view of Dong teach the method according to claim 1. Dong further teaches, wherein generating a quality measure includes determining, by the computer, a level of similarity between an inbound speaker embedding and a corresponding enrolled speaker embedding for an enrolled audio signal ( Dong: Para.[0049], Fig. 3, the acoustic quality determinator 221 extracts one or more features from the digital audio signal, obtains one or more acoustic feature vectors ( inbound speaker embedding ) of a certain length, and inputs the one or more acoustic feature vectors and acoustic feature vectors of a target audio signal (corresponding enrolled speaker embedding for an enrolled audio signal) into the input layer of the first convolutional neural network model. The first convolutional neural network model calculates the degree of similarity between the digital audio signal and the target audio signal).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Dong’s teaching of a vocal training apparatus having a microphone and a vocal analyzer, a vocal training method , into the system and method of speaker identification by analyzing speech signals, taught by Lesso, because, by determining the acoustic quality of different user, a personalized data base for each user based on the identification information of the user can be established and user can be identified authentically. (Dong, Para.[0042]).
Claim 17 is a system claim performing the steps in method claim 7 above and as such, claim 17 is similar in scope and content to claim 7 and therefore, claim 17 is rejected under similar rationale as presented against claim 7 above.
Claims 2-4, 8, 12-14 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Lesso et al. ( US 20190333522 A1), hereinafter referenced as Lesso, in view of Dong et al. (US 20190124441 A1), hereinafter referenced as Dong, further in view of Park et al. (US 20200286489 A1), hereinafter referenced as Park.
Regarding Claim 2, Lesso in view of Dong teach the method according to claim 1. Lesso in view of Dong fail to explicitly teach the claimed, further comprising generating, by the computer, the initial similarity score by executing a second machine-learning architecture using as input an inbound speaker embedding and an enrolled voiceprint for the enrolled speaker.
However, Park does teach the claimed, further comprising generating, by the computer, the initial similarity score by executing a second machine-learning architecture using as input an inbound speaker embedding and an enrolled voiceprint for the enrolled speaker ( Park: Para.[0126]-[0128], Fig. 8, the recognition apparatus compares at least one input feature vector 860 to at least one registered feature vector 835 or representative registered feature vector 840 of a registered user stored in the registration DB constructed in the registration process. A similarity score is calculated between the input feature vector 860 ( speaker embedding) and the registered feature vector 835 (enrolled voiceprint) , where neural network 830 is used).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Park’s teaching of a method and apparatus with speaker recognition registration, into the system and method of speaker identification by analyzing speech signals, taught by Lesso in view of Dong, because, by registering a feature vector of the speech signal of a speaker and a preset noise signal in the registration process, performing verification in an actual environment which is different from the registration environment and is exposed to various types of noise, it is possible to improve a level of performance in the verification. (Park, Para.[0081]).
Claim 12 is a system claim performing the steps in method claim 2 above and as such, claim 12 is similar in scope and content to claim 2 and therefore, claim 12 is rejected under similar rationale as presented against claim 2 above.
Regarding Claim 3, Lesso in view of Dong, further in view of Park teach the method according to claim 2. Park further teaches, further comprising generating, by the computer, the enrolled voiceprint by combining a plurality of enrollee embeddings ( Park: Para.[0136], Fig. 10, the speaker identification method may generate a feature vector for each of a plurality of speakers. For example, the speaker identification method may generate and register a feature vector 1020 for registered speech signals 1010 of N speakers using a feature vector generator 1015, and construct a registration DB for the N speakers).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Park’s teaching of a method and apparatus with speaker recognition registration, into the system and method of speaker identification by analyzing speech signals, taught by Lesso in view of Dong, because, by registering a feature vector of the speech signal of a speaker and a preset noise signal in the registration process, performing verification in an actual environment which is different from the registration environment and is exposed to various types of noise, it is possible to improve a level of performance in the verification. (Park, Para.[0081]).
Claim 13 is a system claim performing the steps in method claim 3 above and as such, claim 13 is similar in scope and content to claim 3 and therefore, claim 13 is rejected under similar rationale as presented against claim 3 above.
Regarding Claim 4, Lesso in view of Dong, further in view of Park teach the method according to claim 3. Park further teaches, further comprising generating, by the computer, the plurality of enrollee embeddings by executing the second machine-learning architecture using as input a plurality of enrollee audio samples, wherein the inbound speaker embedding is generated by executing the second machine-learning architecture using as input the feature vector for the one or more acoustic features of the inbound audio signal ( Park: Para.[0136], Fig. 10, the speaker identification method may generate and register a feature vector 1020 for registered speech signals 1010 of N speakers using a feature vector generator 1015 ( neural network), and construct a registration DB for the N speakers. Para.[0126], Fig.8, the feature vector generator 855 may generate the input feature vector 860 using a neural network ).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Park’s teaching of a method and apparatus with speaker recognition registration, into the system and method of speaker identification by analyzing speech signals, taught by Lesso in view of Dong, because, by registering a feature vector of the speech signal of a speaker and a preset noise signal in the registration process, performing verification in an actual environment which is different from the registration environment and is exposed to various types of noise, it is possible to improve a level of performance in the verification. (Park, Para.[0081]).
Claim 14 is a system claim performing the steps in method claim 4 above and as such, claim 14 is similar in scope and content to claim 4 and therefore, claim 14 is rejected under similar rationale as presented against claim 5 above.
Regarding Claim 8, Lesso in view of Dong teach the method according to claim 1. Lesso in view of Dong fail to explicitly teach the claimed, further comprising: receiving, by the computer, one or more clean enrollment audio signals for the enrolled speaker; generating, by the computer, one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation; and extracting, by the computer, one or more enrolled quality embeddings for the enrolled speaker by applying a second machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals.
However, Park does teach the claimed, further comprising: receiving, by the computer, one or more clean enrollment audio signals for the enrolled speaker ( Park: Para.[0121], Fig. 8, in the registration process, a registration apparatus receives the speech signal 810 of a speaker ( clean signal));
generating, by the computer, one or more degraded enrollment audio signals corresponding to the one or more clean enrollment audio signals according to a type of degradation ( Park: Para.[0121], Fig. 8, additive noise 815 or channel noise 820 is added to the speech signal to synthesize the signal ( degraded signal));
and extracting, by the computer, one or more enrolled quality embeddings for the enrolled speaker by applying a second machine-learning architecture on the one or more clean enrollment audio signals and the one or more degraded enrollment audio signals ( Park: Para.[0121], Fig. 8, registered feature vector 835 ( enrolled quality embedding) is generated for the synthesized speech signal by the feature vector generator 830 ( neural network) and saved in the registration DB. Para.[0122],[0126] Fig. 8, the recognition apparatus receives an input speech signal 845 of a speaker. A feature vector generator 855 ( neural network) of the recognition apparatus generates an input feature vector 860).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Park’s teaching of a method and apparatus with speaker recognition registration, into the system and method of speaker identification by analyzing speech signals, taught by Lesso in view of Dong, because, by registering a feature vector of the speech signal of a speaker and a preset noise signal in the registration process, performing verification in an actual environment which is different from the registration environment and is exposed to various types of noise, it is possible to improve a level of performance in the verification. (Park, Para.[0081]).
Claim 18 is a system claim performing the steps in method claim 8 above and as such, claim 18 is similar in scope and content to claim 8 and therefore, claim 18 is rejected under similar rationale as presented against claim 8 above.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Lesso et al. ( US 20190333522 A1), hereinafter referenced as Lesso, in view of Dong et al. (US 20190124441 A1), hereinafter referenced as Dong, further in view of Gupta et al. (US 20200184967 A1), hereinafter referenced as Gupta.
Regarding Claim 6, Lesso in view of Dong teach the method according to claim 1. Lesso in view of Dong fail to explicitly teach the claimed, wherein generating the one or more quality measures includes: generating, by the computer, a plurality of speech segments from the inbound audio signal; and determining, by the computer, a total duration of speech based upon the plurality of speech segments. Gupta
However, Gupta does teach the claimed wherein generating the one or more quality measures includes: generating, by the computer, a plurality of speech segments from the inbound audio signal ( Gupta: Para.[0117], Fig.7, TTS storage unit 772 stores one or more voice corpuses (e.g., voice inventories 778a-n). Each voice inventory may correspond to various segments of audio that was recorded by a speaking human, such as a voice actor, where the segments are stored in an individual inventory 778 as acoustic units);
and determining, by the computer, a total duration of speech based upon the plurality of speech segments ( Gupta: Para.[0117], each stored unit includes information such as pitch, duration etc.).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Gupta’s teaching of Speech Processing system, into the system and method of speaker identification by analyzing speech signals, taught by Lesso in view of Dong, because, this would improve the speech processing system by being able to "hand off" utterances from one speech processing system to another, or from one component of a speech processing system to another component of another speech processing system, while at the same time indicating to the user that such a hand-off has happened, to provide a desirable customer experience. (Gupta, Para. [0019]).
Claim 16 is a system claim performing the steps in method claim 6 above and as such, claim 16 is similar in scope and content to claim 6 and therefore, claim 16 is rejected under similar rationale as presented against claim 6 above.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Lesso et al. ( US 20190333522 A1), hereinafter referenced as Lesso, in view of Dong et al. (US 20190124441 A1), hereinafter referenced as Dong, further in view of Park et al. (US 20200286489 A1), hereinafter referenced as Park, further in view of Lomada et al. (US 20200107072 A1), hereinafter referenced as Lomada.
Regarding Claim 9, Lesso in view of Dong, further in view of Park teach the method according to claim 8. Lesso in view of Dong, further in view of Park fail to explicitly teach the claimed, further comprising enabling, by the computer, classification layers and loss layers of the second machine-learning architecture in a training phase of the second machine-learning architecture.
However, Lomada does teach the claimed, further comprising enabling, by the computer, classification layers and loss layers of the second machine-learning architecture in a training phase of the second machine-learning architecture ( Lomada: Para.[0040], the LSTM autoencoder model includes additional layers during training and/or execution, such as an embedding layer, a dense layer, a classification layer, and/or a loss layer).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Lomada’s teaching of system and method for generating user embeddings utilizing an LSTM autoencoder model that captures a history of changes to user trait data, into the system and method, taught by Lesso in view of Dong further in view of Park, because, the user embeddings system utilizing the learned user embeddings can more accurately predict the outcome of a task than conventional systems. (Lomada, Para. [0030]).
Claim 19 is a system claim performing the steps in method claim 9 above and as such, claim 19 is similar in scope and content to claim 9 and therefore, claim 19 is rejected under similar rationale as presented against claim 9 above.
Claims 10 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Lesso et al. ( US 20190333522 A1), hereinafter referenced as Lesso, in view of Dong et al. (US 20190124441 A1), hereinafter referenced as Dong, further in view of Park et al. (US 20200286489 A1), hereinafter referenced as Park, further in view of Zhu et al. (WO 2020098158 A1), hereinafter referenced as Zhu.
Regarding Claim 10, Lesso in view of Dong, further in view of Park teach the method according to claim 8. Lesso in view of Dong, further in view of Park fail to explicitly teach the claimed, further comprising disabling, by the computer, classification layers and loss layers of the second machine-learning architecture in a deployment phase of the second machine-learning architecture.
However, Zhu does teach the claimed, further comprising disabling, by the computer, classification layers and loss layers of the second machine-learning architecture in a deployment phase of the second machine-learning architecture ( Zhu: Page 9, para.[1], when the pedestrian re-recognition model is constructed for pedestrian recognition or testing ( deployment), the extracted pedestrian image features are only output by nonlinear transformation through the Leaky ReLu activation function, and no longer pass through the Dropout layer and the final fully connected layer for classification ( disabling )).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Zhu’s teaching of image recognition using stitched neural network, into the system and method, taught by Lesso in view of Dong further in view of Park, because, by providing a method for pedestrian re-identification, can improve the accuracy of pedestrian recognition, avoid the problem of insufficient generalization of feature extraction templates, and enable pedestrian recognition in multiple scenarios. (Zhu, Page 5, para.[2] ).
Claim 20 is a system claim performing the steps in method claim 10 above and as such, claim 20 is similar in scope and content to claim 10 and therefore, claim 20 is rejected under similar rationale as presented against claim 10 above.
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant's disclosure.
Finkelstein et al. (US 20180293221 A1) teaches a method to execute computer-actionable directives conveyed in human speech comprises: receiving audio data recording speech from one or more speakers; converting the audio data into a linguistic representation of the recorded speech; detecting a target corresponding to the linguistic representation; committing to the data structure language data associated with the detected target and based on the linguistic representation; parsing the data structure to identify one or more of the computer-actionable directives; and submitting the one or more of the computer-actionable directives to the computer for processing.
Stafylakis et al. (US 11948582 B2) teaches a system which includes an interactive voice recognition (IVR) module arranged to perform a speech conversation with a first user and receive a first user identifier, where the speech conversation has an interaction context based on a subject matter of the speech conversation. The system includes a datastore arranged to store a group of active words associated with the interaction context and store first user voiceprints derived from pre-captured audio of the first user, where each active word is selected based on one or more selection criterion derived from conversations of a population of users. An automated speech recognition (ASR) module is arranged to perform speech recognition of the first user audio provided during the speech conversation. A voice biometric (VB) module is arranged to generate captured voiceprints and determine a similarity score based on comparisons of captured voiceprints with first user voiceprints.
Zhang et al. (US 10621991 B2) teaches a speaker recognition system includes a previously-trained joint neural network. An enrollment machine of the speaker recognition system is configured to operate the previously-trained joint neural network to enroll a new speaker based on audiovisual data featuring the newly enrolled speaker. A recognition machine of the speaker recognition system is configured to operate the previously-trained joint neural network to recognize a previously-enrolled speaker based on audiovisual data featuring the previously-enrolled speaker.
Chao et al. (Deep Speaker: an End-to-End Neural Speaker Embedding System, arXiv: 1705.02304v1 [cs.CL] 5 May, 2017 ) teaches a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce utterance-level speaker embeddings, and train using triplet loss based on cosine similarity. Experiments on three distinct datasets suggest that Deep Speaker outperforms a DNN-based i-vector base line. For example, Deep Speaker reduces the verification equal error rate by 50% (relatively) and improves the identification accuracy by 60% (relatively) on a text-independent dataset. Results has been presented that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NADIRA SULTANA whose telephone number is (571)272-4048. The examiner can normally be reached M-F,7:30 am-5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Paras D. Shah can be reached on (571) 270-1650. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/NADIRA SULTANA/Examiner, Art Unit 2653
Prosecution Insights