DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 3/6/2026 has been entered.
Notice of Pre-AIA or 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 .
Response to Amendment
This communication is responsive to the applicant’s amendment dated 2/27/2026. The applicant amended claims 1 and 11.
Response to Arguments
Applicant's arguments with respect to the Double Patenting Rejection (see Remarks, pg. 6, line 10-21 filed 2/27/2026 have been fully considered but they are not persuasive.
The applicant argues that the rejection is moot in view of the amendments in the first generating limitation and the second receiving limitation in the independent claims. In particular, the applicant specifies a time when these limitations are taking place (enrollment operation phase and a deployment operation phase). The examiner respectfully disagrees. The examiner believes the claims in the issued patent could be occurring during the same time frame. After searching the specification of the issued patent, similar time frames are mentioned. Additionally, the applicant has provided minimum to no arguments of how the claimed limitations are different from those in the issued patent. Therefore, the Double Patenting rejection is maintained.
Applicant's arguments with respect to 35 U.S.C. 103 filed 2/27/2026 have been fully considered but they are not persuasive.
The applicant argues that the cited references do not teach, “generating, by the computer in the enrollment operation phase, an enrollment level in the enrolled profile for the enrolled speaker based upon one or more identifications of the one or more input data types of the enrollment data”, “receiving, by the computer executing deployment operations of a deployment operation phase, one or more inbound speaker inputs for an inbound speaker, the one or more inbound speaker inputs comprising an inbound audio signal and inbound contact data”, and “generating, by the computer in the deployment operation phase, an authentication score for the inbound speaker based on the enrolled voiceprint, the enrollment level in the enrolled profile, and an inbound voiceprint for the inbound speaker based on the inbound audio signal”. Given the amendments and request for continued examination, a new ground of rejection is provided below.
Next, the applicant argues that Zeppenfeld fails to teach “generating, in an enrollment phase, an enrollment level in an enrollment profile for an enrolled speaker based on the types of enrollment data”. In particular, the applicant argues that Zeppenfeld authenticates during the call and not during an enrollment phase. The examiner respectfully disagrees. Paragraph [0050] of Zeppenfeld states, “Enrolled voiceprints 618 may indicate to an agent 124 the quality of a voiceprint and how long a voiceprint has been stored by the system using voiceprint maturity. This information may be displayed in a variety of manners, such as using color-coding, a date range, a percentage, or any other fashion that will indicate to the agent 124 the quality and maturity of voiceprints. Voiceprint quality may increase when a user's account has multiple stored copies of voiceprints as opposed to just one. Voiceprint maturity may indicate the amount of time the voiceprint has been stored by the system. Real-time voice 620 may indicate the caller talk time and audio quality, both additional factors that can be used when computing the initial scores, confidence interval score, and overall identification confidence score”. Here the examiner interprets color-coding, percentage, or any other fashion that will indicate quality and maturity of voiceprint as the enrollment level. The examiner interprets the voiceprint to the be the enrollment data and the user’s account as the enrolled profile. Finally, the examiner interprets the various scores to relate the authentication score for the inbound speaker.
Lastly, the applicant has requested some clarification of the mapping. Given the amendments and the request for continued examination, the examiner has adjusted the mapping to help clarify the rejection. As a result, the 35 U.S.C. 103 rejection is maintained.
Double Patenting
The nonstatutory 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 nonstatutory 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 nonstatutory 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 nonstatutory 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 eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claim 1 and 11 rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 and 11 of U.S. Patent No. 11783839 B2(Application No: 17/491,363). Although the claims at issue are not identical, they are not patentably distinct from each other because removing inherent and/or unnecessary limitations/step and rearranging the claims would be within the level of one of ordinary skill in the art. It is well settled that the omission of an element, and its function is an obvious expedient if the remaining elements perform the same function as before. In re Karlson, 136 USPQ 184 (CCPA 1963). Also note Ex parte Rainu, 168 USPQ 375 (Bd. App. 1969). Omission of a reference element or step whose function is not needed would be obvious to one of ordinary skill in the art.
Instant Application No: 17/491,312
Issued Patent no: US 11783839 B2 (Application No: 17/491,363)
A computer-implemented method comprising:
receiving, by a computer executing enrollment operations of an enrollment operation phase, one or more enrollment inputs for an enrolled speaker having an enrolled profile, the one or more enrollment inputs comprising one or more enrollment audio signals and enrollment data, the enrollment data comprising one or more input data types;
executing, by the computer in the enrollment operation phase, a neural network using the one or more enrollment audio signals to generate an enrolled voiceprint, the neural network trained to extract a voiceprint embedding from an input audio signal;
generating, by the computer in the enrollment operation phase, an enrollment level in the enrolled profile for the enrolled speaker based upon one or more identifications of the one or more input data types of the enrollment data;
receiving, by the computer executing deployment operations of a deployment operation phase, one or more inbound speaker inputs for an inbound speaker, the one or more inbound speaker inputs comprising an inbound audio signal and inbound contact data; and
generating, by the computer in the deployment operation phase, an authentication score for the inbound speaker based on the enrolled voiceprint, the enrollment level in the enrolled profile, and an inbound voiceprint for the inbound speaker based on the inbound audio signal.
A computer-implemented method comprising:
receiving, by the computer from a call center server, one or more enrollment inputs for an enrolled speaker, the one or more enrollment inputs including enrollment call metadata;
determining, by the computer, an enrollment level based upon one or more characteristics of the enrollment inputs including the enrollment call metadata, the one or more characteristics including one or more temporal characteristics associated with the enrollment inputs;
generating, by the computer, an enrolled profile for the enrolled speaker according to the enrollment level and based on the one or more characteristics;
receiving, by the computer from the call center server, one or more inbound inputs for an inbound speaker, the one or more inbound inputs including inbound call metadata;
determining, by the computer, an authentication level for the inbound speaker using inbound contact data of the one or more inbound inputs including the inbound call metadata;
generating, by the computer, an authentication score for the inbound speaker based upon the inbound contact data, the authentication level, and the enrollment level; and
transmitting, by the computer to the call center server, a message for authenticating the inbound call based upon the authentication score.
11. A system comprising:
a database configured to store a plurality of enrollment inputs; and
a computer comprising a processor configured to:
receive, executing enrollment operations of an enrollment operation phase, one or more enrollment inputs for an enrolled speaker having an enrolled profile, the one or more enrollment inputs comprising one or more enrollment audio signals and enrollment data, the enrollment data comprising one or more input data types;
execute, in the enrollment operation phase, a neural network using the one or more enrollment audio signals to generate an enrolled voiceprint, the neural network trained to extract a voiceprint embedding from an input audio signal;
generate, in the enrollment operation phase, an enrollment level for the enrolled speaker in the enrolled profile based upon one or more identifications of the one or more input data types of the enrollment data;
receive, executing deployment operations of a deployment operation phase, one or more inbound speaker inputs for an inbound speaker, the one or more inbound speaker inputs comprising an inbound audio signal and inbound contact data; and
generate, in the deployment operation phase, an authentication score for the inbound speaker based on the enrolled voiceprint, the enrollment level in the enrolled profile, and an inbound voiceprint for the inbound speaker based on the inbound audio signal.
11. A system comprising:
a computer comprising a processor configured to:
receive one or more enrollment inputs for an enrolled speaker from a call center server, the one or more enrollment inputs including enrollment call metadata;
determine an enrollment level based upon one or more characteristics of the enrollment inputs including the enrollment call metadata, the one or more characteristics including one or more temporal characteristics associated with the enrollment inputs;
generate an enrolled profile for the enrolled speaker according to the enrollment level and based on the one or more characteristics;
receive one or more inbound inputs for an inbound speaker from the call center server, the one or more inbound inputs including inbound call metadata;
determine an authentication level for the inbound speaker using inbound contact data of the one or more inbound inputs including the inbound call metadata;
generate an authentication score for the inbound speaker based upon the inbound contact data, the authentication level, and the enrollment level; and
transmit, to the call center server, a message for authenticating the inbound call based upon the authentication score.
Claim Rejections - 35 USC § 103
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, 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 and 11 are rejected under 35 U.S.C. 103 as being unpatentable over Zeppenfeld et al. US 20140254778 A1 (hereinafter Zeppenfeld) in view of Khoury et al. US 9824692 B1 (hereinafter Khoury).
Regarding claims 1 and 11, Zeppenfeld teaches a computer implemented method; and a system comprising:
a database configured to store a plurality of enrollment inputs (FIG. 3, 322, 324, 326, 328);
and a computer comprising a processor configured to (FIG. 7, 700, 706);
receiving, by a computer executing enrollment operations of an enrollment operation phase, one or more enrollment inputs for an enrolled speaker having an enrolled profile, the one or more enrollment inputs comprising one or more enrollment audio signals and enrollment data, the enrollment data comprising one or input data types (FIG. 3, 302, [0036] “incoming calls may be received at a voice capture module 302”, examiner interprets incoming calls to be enrollment audio signals/enrollment inputs; [0037] “Unauthorized database 314 may store voice that has been determined to be fraudulent, whether for a particular account or for all accounts. Finally, profiling engine 304 may also include a metadata profile manager 316 that uses database 318 to store the described metadata”, examiner interprets accounts to be associated with enrolled profiles for enrolled speakers; [0036] “FIG. 3 illustrates an exemplary system 300 for evaluating and storing voice prints. System 300 may be part of, or separate from, system 200”, examiner interprets this phase to be the enrollment phase and the voice prints to be the enrollment data.
executing, by the computer in the enrollment operation phase, a neural network using the one or more enrollment audio signals to generate an enrolled voiceprint ([0019] “The voice print may include a collection of features that are extracted from an audio signal, of the individual's voice, and encoded within a specific statistical framework”, examiner interprets statistical framework to be the voiceprint embedding ; [0033] “The resulting identification confidence score may be graded and presented to a call agent 124 in numerical form, using color coding (e.g., red, yellow, or green), or any other way, as described below with reference to FIGS. 5 and 6A-C. While one example of calculating an identification confidence score has been provided, other calculation methods, such as a nonlinear calculation, weighted calculation, or machine learning with neural networks, may also be used”);
generating, by the computer in the enrollment operation phase, an enrollment level in the enrolled profile for the enrolled speaker based upon one or more identifications of the one or more input data types of the enrollment data ([0050] “Enrolled voiceprints 618 may indicate to an agent 124 the quality of a voiceprint and how long a voiceprint has been stored by the system using voiceprint maturity. This information may be displayed in a variety of manners, such as using color-coding, a date range, a percentage, or any other fashion that will indicate to the agent 124 the quality and maturity of voiceprints. Voiceprint quality may increase when a user's account has multiple stored copies of voiceprints as opposed to just one. Voiceprint maturity may indicate the amount of time the voiceprint has been stored by the system. Real-time voice 620 may indicate the caller talk time and audio quality, both additional factors that can be used when computing the initial scores, confidence interval score, and overall identification confidence score”, the examiner interprets color-coding, percentage, or any other fashion that will indicate quality and maturity of voiceprint as the enrollment level. Additionally, the examiner interprets the voiceprint to the be the enrollment data and the user’s account as the enrolled profile. Lastly, the examiner interprets this enrollment information to be receive during enrollment operation phase and not during the call.)
receiving, by the computer executing deployment operations of a deployment operation phase, one or more inbound speaker inputs for an inbound speaker, the one or more inbound speaker inputs comprising an inbound audio signal and inbound contact data (FIG. 2, 202, 204, [0021] “At step 202, system 100 may receive a call. Next, method 200 may obtain metadata and voice prints from a caller at step 204”, examiner interprets this to be done during the call or the deployment phase);
generating, by the computer in the deployment operation phase, an authentication score for the inbound speaker based on the enrolled voiceprint, the enrollment level in the enrolled profile (FIG. 2, 214, [0033] Finally, an identification confidence score may be generated at step 214. The identification confidence score may be any combination of the initial score(s) and the confidence interval score), and an inbound voiceprint for the inbound speaker based on the inbound audio signal (FIG. 2, 204, [0021] “method 200 may obtain metadata and voice prints from a caller at step 204”);
Zeppenfeld fails to teach the neural network trained to extract a voiceprint embedding from an input audio signal
However, Khoury teaches the neural network trained to extract a voiceprint embedding from an input audio signal ([Column 7, line 30-40] “in FIG. 3A, each of the first, second, and third feed-forward neural networks 212, 222, 232 may comprise a first convolutional layer connected to a max-pooling layer, a second convolutional layer followed by a second max-pooling layer, a subsequent fully connected layer, and an output layer which comprises the embedding vector. Upon conclusion of training, however, the output layer of each of the feed-forward neural networks 212, 222, 232 will be configured to produce a feature representation (i.e., voiceprint) of the inputted sample”)
Zeppenfeld in view of Khoury are considered to be analogous to the claimed invention because both are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld with the technique of generating voiceprint embeddings from audio using neural networks taught by Khoury in order to improve a system that utilizes a deep neural network with a triplet network architecture to train a front-end feature extractor, which is used to perform a task of verification of a speaker's identity (see Khoury [Column 1, line 51-54]).
Claims 2-10 and 12-20 are rejected under 35 U.S.C. 103 as being unpatentable over Zeppenfeld in view of Khoury, as shown in claim 1, in further view of Krishnamoorthy et al. US 10490195 B1 (hereinafter Krishnamoorthy).
Regarding claim 2 and 12 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach wherein an input includes at least one of an inbound input and an enrollment input, and wherein the input includes one or more knowledge responses.
However, Krishnamoorthy teaches wherein an input includes at least one of an inbound input and an enrollment input, and wherein the input includes one or more knowledge responses. (speaker ID sub-module 369 compares the input iVector (inbound input) with the iVectors stored (enrollment input) associated with information (knowledge responses) from identified user accounts; column 20, line 41-63).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of using knowledge responses taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 3 and 13 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach transmitting, by the computer, a prompt for an input to an end-user device, wherein the input includes at least one of an inbound input and an enrollment input, and wherein the input includes a response to the prompt.
However, Krishnamoorthy discloses transmitting, by the computer, a prompt for an input to an end-user device, wherein the input includes at least one of an inbound input and an enrollment input, and wherein the input includes a response to the prompt. (The speech processing system may determine the intent of an utterance by examining the enrolled inputs with the inbound input to transmit a response to the user’s device; column 9, line 33-44; column 21, line 14-34).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of transmitting a prompt taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 4 and 14 Zeppenfeld in view of Khoury fails discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach extracting, by the computer, an enrollment deviceprint using the enrollment data; extracting, by the computer, an inbound deviceprint using the inbound contact data; and generating, by the computer, a device similarity score using the inbound deviceprint and the enrollment deviceprint, wherein the authentication score for the inbound speaker is further based upon the device similarity score.
However, Krishnamoorthy discloses extracting, by the computer, an enrollment deviceprint using the enrollment data; extracting, by the computer, an inbound deviceprint using the inbound contact data; (The system can leverage various information (deviceprint) from the account associated with a particular device in order to select relevant utterances for the custom enrollment process; column 35, line 39-44; column 3, line 4-9, column 3, line 22-30); and generating, by the computer, a device similarity score using the inbound deviceprint and the enrollment deviceprint, wherein the authentication score for the inbound speaker is further based upon the device similarity score. (The user recognition module determines scores for incoming utterances (based on vector data) to determine their accuracy; column 28, line 10-20).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of extracting deviceprints taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 5 and 15 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach extracting, by the computer, an enrollment behaviorprint using the enrollment data; extracting, by the computer, an inbound behaviorprint using the inbound contact data; and generating, by the computer, a behavior similarity score using the inbound behaviorprint and the enrollment behaviorprint, wherein the authentication score for the inbound speaker is further based upon the behavior similarity score.
However, Krishnamoorthy teaches extracting, by the computer, an enrollment behaviorprint using the enrollment data; extracting, by the computer, an inbound behaviorprint using the inbound contact data; (Information (behaviorprint) that can be gathered related to the utterances (inbound contact data) include the history of how the user has used the device(column 4 lines 28-40; column 7 lines 56-67; column 8, lines 48-60) ; and generating, by the computer, a behavior similarity score using the inbound behaviorprint and the enrollment behaviorprint, wherein the authentication score for the inbound speaker is further based upon the behavior similarity score. (The enrollment utterances are formed into a vector and later scored in comparison with inbound utterances; column 9, line 10-21; column 28, line 10-20).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of extracting behaviorprints taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 6 and 16 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach authenticating, by the computer, the inbound speaker as the enrolled speaker based in part upon determining that the authentication score satisfies an authentication threshold score.
However, Krishnamoorthy discloses authenticating, by the computer, the inbound speaker as the enrolled speaker based in part upon determining that the authentication score satisfies an authentication threshold score. (When the system compares the vector from the inbound spoken utterance and the stored enrollment vector, a certain threshold score exists that confirms the utterance came from a specific individual; column 9, line 45-56).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of authenticating based off a threshold taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 7 and 17 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach authenticating, by the computer, the inbound speaker as the enrolled speaker based in part upon determining that the authentication level satisfies the enrollment level
However, Krishnamoorthy discloses authenticating, by the computer, the inbound speaker as the enrolled speaker based in part upon determining that the authentication level satisfies the enrollment level (The user (enrolled speaker) goes through a series of phrases to generate a vector that will be used as the user’s profile. When the user (inbound speaker) utilizes voice recognition, a similar vector will be created from the spoken utterance. When a comparison is done between the two vectors a certain threshold value (authentication level) indicates a match; column 3 line 64- column 4, line 18; column 9, line 10-21).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of authenticating based off an enrollment level taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 8 and 18 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld in view of Khoury fails to teach generating, by the computer, a risk score for the enrollment input based upon at least one of a global risk factor and a local risk factor, wherein the enrollment level is based in part upon the risk score
However, Krishnamoorthy discloses generating, by the computer, a risk score for the enrollment input based upon at least one of a global risk factor and a local risk factor, wherein the enrollment level is based in part upon the risk score (increasing the confidence level that the enrollment will be successful (generating a risk score for the enrollment input) column 8, line 1-10).
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of generating a risk score taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 9 and 19 Zeppenfeld in view of Khoury discloses the method according to claim 1 and the system according to claim 11, respectively.
Zeppenfeld additionally discloses wherein the enrollment level is determined based upon a relative weight mapped to a corresponding input data type of the one or more input data types ([0028] “The type of metadata may also be weighted to correlate with the likelihood that a piece of metadata authenticates a caller. Names and addresses are publically available and therefore provide low security and would receive a low weighting. Full social security numbers, on the other hand, provide a higher degree of confidence that the caller is an authenticated user, and therefore may receive higher weighting”)
Zeppenfeld in view of Khoury fails to teach wherein the enrollment level is determined based upon a relative weight mapped to a corresponding input data type of the one or more input data types
However, Krishnamoorthy discloses wherein the enrollment level is determined based upon a relative weight mapped to a corresponding input data type of the one or more input data types (certain types of data may be associated with weight. Each user profile may include reliability weight information associated with the data type column 31, line 48-52) which also teaches on this limitation.
Zeppenfeld in view of Khoury in view of Krishnamoorthy are considered to be analogous to the claimed invention because all are in the same field of speaker identification. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified the voice identification systems of Zeppenfeld in view of Khoury with the technique of weight mapping taught by Krishnamoorthy in order to improve the systems, methods, and devices related to establishing speaker profiles for use with voice-controlled devices (see Krishnamoorthy [Column 1, line 51-54]).
Regarding claim 10 and 20 Zeppenfeld in view of Krishnamoorthy in view of Khoury discloses the method according to claim 9 and the system according to claim 19, respectively.
Krishnamoorthy additionally discloses the one or more input data types of the enrollment inputs include at least one of: a weak knowledge based authentication value, a strong knowledge based authentication value (A user profile has training data that corresponds to audio samples associated with a user’s identity. That training data is placed in vector form and compared with a vector of a spoken utterance. The value of the comparison can determine the type of match that is present; (column 27, line 1-10; column 9, line 45-56) a one-time password (In the presence of multiple individuals, user verification may be done through the use of a passcode; column 31, line 21-47), a push notification response (Non-voice activated devices can notify a computing system through a push-to-talk (push notification) device to begin recording; column 11, line 10-32), and an embedding vector (Encoders will output vectors of the same size regardless on the feature values of the input. This ensures comparing embedded vectors. column 25, lines 36-50).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Chen et al. (US 20180358020 A1) teaches a method, apparatus, and system for speaker verification. The method includes: acquiring an audio recording; extracting speech signals from the audio recording; extracting features of the extracted speech signals; and determining whether the extracted speech signals represent speech by a predetermined speaker based on the extracted features and a speaker model trained with reference voice data of the predetermined speaker.
Jaiswal et al. (US 20140119520 A1) teaches a method and system for using conversational biometrics and speaker identification and/or verification to filter voice streams during mixed mode communication. The method includes receiving an audio stream of a communication between participants. Additionally, the method includes filtering the audio stream of the communication into separate audio streams, one for each of the participants. Each of the separate audio streams contains portions of the communication attributable to a respective participant. Furthermore, the method includes outputting the separate audio streams to a storage system.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ZEESHAN SHAIKH whose telephone number is (703)756-1730. The examiner can normally be reached Monday-Friday 7:30AM-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, Richemond Dorvil can be reached at (571) 272-7602. 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.
/ZEESHAN MAHMOOD SHAIKH/Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658