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 .
DETAILED ACTION
This office action is in response to application 18/937,161, which was filed 11/05/24. Claims 1-15 are pending in the application and have been considered.
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 1-15 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
Claim 1 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites “capturing, by an electronic device, audio data of a user speaking during an authentication transaction; dividing the audio data into segments; determining a quality control vector for each segment; determining whether each segment is of adequate quality based on the quality control vector for the respective segment; calculating a voice replay score and a voice cloning detection score for each adequate quality segment; determining, by a trained machine learning model operated by the electronic device, a weight for each adequate quality segment; applying the weight determined for each adequate quality segment to the voice replay and voice cloning scores calculated for the respective adequate quality segment and calculating a decision score; comparing the decision score against a threshold value; and in response to determining the decision score satisfies the threshold value, determining the captured audio data is genuine”.
The limitation of “capturing, by an electronic device, audio data of a user speaking during an authentication transaction”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for “by an electronic device”, “capturing audio data of a user speaking during an authentication transaction” in the context of this claim encompasses listening to a user speaking during an authentication transaction and writing down a transcript on a sheet of paper.
Similarly, the limitation of “dividing the audio data into segments”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “dividing the audio data into segments” in the context of this claim encompasses mentally dividing transcript into segments on the paper.
Similarly, the limitation of “determining a quality control vector for each segment” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining a quality control vector for each segment” in the context of this claim encompasses mentally determining and writing down a quality score for each word on the transcript for the segment.
Similarly, the limitation of “determining whether each segment is of adequate quality based on the quality control vector for the respective segment” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “determining whether each segment is of adequate quality based on the quality control vector for the respective segment” in the context of this claim encompasses mentally determining whether each segment is of adequate quality based on the quality control vector for the respective segment.
Similarly, the limitation of “calculating a voice replay score and a voice cloning detection score for each adequate quality segment” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “calculating a voice replay score and a voice cloning detection score for each adequate quality segment” in the context of this claim encompasses mentally calculating a voice replay score and a voice cloning detection score for each adequate quality segment.
Similarly, the limitation of “determining, by a trained machine learning model operated by the electronic device, a weight for each adequate quality segment”, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for “by a trained machine learning model operated by the electronic device”, “determining a weight for each adequate quality segment” in the context of this claim encompasses mentally determining a weight for each adequate quality segment.
Similarly, the limitation of “applying the weight determined for each adequate quality segment to the voice replay and voice cloning scores calculated for the respective adequate quality segment and calculating a decision score” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “applying the weight determined for each adequate quality segment to the voice replay and voice cloning scores calculated for the respective adequate quality segment and calculating a decision score” in the context of this claim encompasses mentally applying the weight determined for each adequate quality segment to the voice replay and voice cloning scores calculated for the respective adequate quality segment and mentally calculating a decision score.
Similarly, the limitation of “comparing the decision score against a threshold value” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “comparing the decision score against a threshold value” in the context of this claim encompasses mentally comparing the decision score against a threshold value.
Finally, the limitation of “in response to determining the decision score satisfies the threshold value, determining the captured audio data is genuine” as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind. For example, “in response to determining the decision score satisfies the threshold value, determining the captured audio data is genuine” in the context of this claim encompasses mentally in response to determining the decision score satisfies the threshold value, determining the captured audio data is genuine.
If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. This judicial exception is not integrated into a practical application. In particular, the claim only recites two additional elements – “electronic device” and “trained machine learning model”. The computing elements in this step are recited at a high-level of generality (i.e., as a generic electronic device and a generic trained machine learning model) such that they amount to no more than mere instructions to apply the exception using generic computer elements. 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. The claim is directed to an abstract idea. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computing device to perform the capturing of audio data amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
Specifically with respect to Step 2A, Prong Two, of the Alice/Mayo test, the judicial exception is not integrated into a practical application. Claim 1 does not recite any limitations that are not mental steps.
Specifically with respect to Step 2B of the Alice/Mayo test, “the claim as a whole does not amount to significantly more than the exception itself (there is no inventive concept in the claim)”. MPEP 2106.05 Il. There are no limitations in claim 1 outside of the judicial exception. As a whole, there does not appear to contain any inventive concept. As discussed above, claim 1 is a mental process that pertains to the mental process of determining whether captured audio data is genuine based on a score, which can be performed entirely by a human with physical aids.
Dependent claims 2-5 depend from claim 1, do not remedy any of the deficiencies of claim 1, and therefore are rejected on the same grounds as claim 1 above.
Generally, claims 2-5 merely recite additional steps for determining whether captured audio data is genuine based on a score, all of which could be performed mentally or by writing down relationships with a pen and paper, and do not amount to anything more than substantially the same abstract idea as explained with respect to claim 1.
Specifically:
Claim 2 recites “determining the captured audio data is fraudulent in response to determining the decision score fails to satisfy the threshold value” which could be performed by mentally determining the captured audio data is fraudulent in response to determining the decision score fails to satisfy the threshold value.
Claim 3 recites “discarding segments of inadequate quality” which could be performed by transcribing the transcript to a new sheet of paper copying only segments of adequate quality, and discarding the old paper.
Claim 4 recites “the segments vary in duration” which could be performed by writing down segments that vary in duration.
Claim 5 recites “said step of calculating the decision score comprising combining the determined weights” which could be performed by mentally combining the determined weights.
In sum, claims 2-5 depend from claim 1 and further recite mental processes as explained above. None of the additional limitations recited in claims 2-5 amount to anything more than the same or a similar abstract idea as recited in claim 1. Nor do any limitations in claims 2-5 (a) integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea or (b) amount to significantly more than the judicial exception. Claims 2-5 are not patent eligible.
Claim 6 is directed to an electronic device that corresponds to the method of claim 1 and is therefore rejected for the same reasons set for the above with respect to claim 1. While claim 6 recites generic computer components (processor, memory, network, instructions), such generic computing components are recited at a high-level of generality (i.e., as a generic processor, memory, network, and instructions performing a generic computer functions) such that they amount to no more than mere instructions to apply the exception using generic computer components. 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. The claim is directed to an abstract idea.
Claim 6 does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional limitations of using generic computer components amount to no more than mere instructions to apply the exception using generic computer components. Mere instructions to apply an exception using generic computer components cannot provide an inventive concept. Claim 6 is not patent eligible.
Claims 7-10 depend from claim 6, do not remedy any of the deficiencies of claim 6, and correspond to the subject matter of claims 2-5 above, and therefore are rejected on the same grounds as claims 2-5 and 6 above.
Claim 11 is directed to a non-transitory computer readable storage medium that corresponds to the system of claim 6 and is therefore rejected for the same reasons set forth above with respect to claim 6. Moreover, while claim 11 recites generic computing components (e.g., hardware processor, instructions), such components are only claimed at a high-level of generality and are not sufficient to render the claim subject matter eligible for the same reasons discussed above with respect to claims 6 and 1.
Claims 12-15 depend from claim 11, do not remedy any of the deficiencies of claim 11, and correspond to the subject matter of claims 2-5 above, and therefore are rejected on the same grounds as claims 2-5 and 11 above.
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 1-15 are rejected under 35 U.S.C. 103 as being unpatentable over Khoury et al. (US 20240363100), herein Khoury’100, in view of Khoury et al. (US 20180254046), herein Khoury’046.
Consider claim 1, Khoury’100 discloses a method for enhancing the detection of fraudulent audio data (method for improved means of detecting fraudulent uses of audio-based deepfake technology, [0007]-[0008]) comprising the steps of:
capturing, by an electronic device, audio data of a user speaking during an authentication transaction (end user device uses microphone to capture audio waveform of the caller speaking, [0048], who speaks into a system for authenticating callers for e.g. account access, [0044], [0047], Fig. 1);
dividing the audio data into segments (parsing and segmenting the audio signal into frames or segments, [0056]);
determining a quality control vector for each segment (extracting a set of acoustic quality parameters, [0081-0082], for each segment, [0061], which are used for a quality check, i.e. quality control, [0147]);
determining whether each segment is of adequate quality based on the quality control vector for the respective segment (comparing acoustic parameters for each segment to a quality threshold to determine whether to use the audio for authentication or generate a redo prompt [0146-0148]);
calculating a voice replay score and a voice cloning detection score for each adequate quality segment (audio fingerprint score, which determines whether the audio is a likely replay of the same speech signal audio recording, [0138], and passive liveness score, which indicates the likelihood that the audio is fraudulent, [0127], versus a deepfake, i.e. cloned synthetic voice of the user, [0122]);
determining, by a trained machine learning model operated by the electronic device, a weight for each adequate quality segment (determining a data driven weighted combination of scores, for each segment passing the quality threshold, [0147-0148], by scoring layers, [0141]);
applying the weight determined for each adequate quality segment to voice cloning score calculated for the respective adequate quality segment and calculating a decision score (a weighted combination applies a weight to the passive liveness score to determine a final liveness score, [0148]);
comparing the decision score against a threshold value (comparing the liveness score to a predefined detection threshold value, [0079]); and
in response to determining the decision score satisfies the threshold value, determining the captured audio data is genuine (determining that the input audio is a real human-speaker, as opposed to a presentation attack, [0079]).
Khoury’100 does not specifically mention applying the weight to the voice replay score.
Khoury’046 discloses applying a weight to a voice replay score (at binary classifier, scores are fused by applying weights to the likelihood scores, [0057], including likelihood score for features corresponding to a replay attack, [0047]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Khoury’100 by applying the weight to the voice replay score in order to reduce vulnerability to spoofing attacks, as suggested by Khoury’046 ([0002]). Doing so would have led to predictable results of increased security for voice applications, as suggested by Khoury’046 ([0002]). The references cited are analogous art in the same field of voice authentication.
Consider claim 6, Khoury’100 discloses an electronic device for enhancing the detection of fraudulent audio data (computing device for improved means of detecting fraudulent uses of audio-based deepfake technology, [0007]-[0008], [0092], comprising:
a processor (processor, [0152]); and
a memory configured to store data, said electronic device being associated with a network and said memory being in communication with said processor and having instructions stored thereon which, when read and executed by said processor (program on a memory executed by the processor, [0152], on devices connected to networks, [0051]), cause said electronic device to:
capture audio data of a user speaking during an authentication transaction (end user device uses microphone to capture audio waveform of the caller speaking, [0048], who speaks into a system for authenticating callers for e.g. account access, [0044], [0047], Fig. 1);
divide the audio data into segments (parsing and segmenting the audio signal into frames or segments, [0056]);
determine a quality control vector for each segment (extracting a set of acoustic quality parameters, [0081-0082], for each segment, [0061], which are used for a quality check, i.e. quality control, [0147]);
determine whether each segment is of adequate quality based on the quality control vector for the respective segment (comparing acoustic parameters for each segment to a quality threshold to determine whether to use the audio for authentication or generate a redo prompt [0146-0148]);
calculate a voice replay score and a voice cloning detection score for each adequate quality segment (audio fingerprint score, which determines whether the audio is a likely replay of the same speech signal audio recording, [0138], and passive liveness score, which indicates the likelihood that the audio is fraudulent, [0127], versus a deepfake, i.e. cloned synthetic voice of the user, [0122]);
determine, by a trained machine learning model operated by said electronic device, a weight for each adequate quality segment (determining a data driven weighted combination of scores, for each segment passing the quality threshold, [0147-0148], by scoring layers, [0141]);
apply the weight determined for each adequate quality segment to voice cloning score calculated for the respective adequate quality segment and calculating a decision score (a weighted combination applies a weight to the passive liveness score to determine a final liveness score, [0148]);
compare the decision score against a threshold value (comparing the liveness score to a predefined detection threshold value, [0079]); and
in response to determining the decision score satisfies the threshold value, determine the captured audio data is genuine (determining that the input audio is a real human-speaker, as opposed to a presentation attack, [0079]).
Khoury’100 does not specifically mention applying the weight to the voice replay score.
Khoury’046 discloses applying a weight to a voice replay score (at binary classifier, scores are fused by applying weights to the likelihood scores, [0057], including likelihood score for features corresponding to a replay attack, [0047]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Khoury’100 by applying the weight to the voice replay score for reasons similar to those for claim 6.
Consider claim 11, Khoury’100 discloses a non-transitory computer-readable recording medium in an electronic device for enhancing the detection of fraudulent audio data, the non-transitory computer-readable recording medium storing instructions which when executed by a hardware processor cause the non-transitory recording medium to perform steps (program on a memory executed by the processor, [0152], for improved means of detecting fraudulent uses of audio-based deepfake technology, [0007]-[0008]) comprising:
capturing audio data of a user speaking during an authentication transaction (end user device uses microphone to capture audio waveform of the caller speaking, [0048], who speaks into a system for authenticating callers for e.g. account access, [0044], [0047], Fig. 1);
dividing the audio data into segments (parsing and segmenting the audio signal into frames or segments, [0056]);
determining a quality control vector for each segment (extracting a set of acoustic quality parameters, [0081-0082], for each segment, [0061], which are used for a quality check, i.e. quality control, [0147]);
determining whether each segment is of adequate quality based on the quality control vector for the respective segment (comparing acoustic parameters for each segment to a quality threshold to determine whether to use the audio for authentication or generate a redo prompt [0146-0148]);
calculating a voice replay score and a voice cloning detection score for each adequate quality segment (audio fingerprint score, which determines whether the audio is a likely replay of the same speech signal audio recording, [0138], and passive liveness score, which indicates the likelihood that the audio is fraudulent, [0127], versus a deepfake, i.e. cloned synthetic voice of the user, [0122]);
determining, by a trained machine learning model operated by the electronic device, a weight for each adequate quality segment (determining a data driven weighted combination of scores, for each segment passing the quality threshold, [0147-0148], by scoring layers, [0141]);
applying the weight determined for each adequate quality segment to voice cloning score calculated for the respective adequate quality segment and calculating a decision score (a weighted combination applies a weight to the passive liveness score to determine a final liveness score, [0148]);
comparing the decision score against a threshold value (comparing the liveness score to a predefined detection threshold value, [0079]); and
in response to determining the decision score satisfies the threshold value, determining the captured audio data is genuine (determining that the input audio is a real human-speaker, as opposed to a presentation attack, [0079]).
Khoury’100 does not specifically mention applying the weight to the voice replay score.
Khoury’046 discloses applying a weight to a voice replay score (at binary classifier, scores are fused by applying weights to the likelihood scores, [0057], including likelihood score for features corresponding to a replay attack, [0047]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Khoury’100 by applying the weight to the voice replay score for reasons similar to those for claim 6.
Consider claim 2, Khoury’100 discloses determining the captured audio data is fraudulent in response to determining the decision score fails to satisfy the threshold value (determining that the input audio is a presentation attack using the threshold, [0079]).
Consider claim 3, Khoury’100 discloses discarding segments of inadequate quality (segments below quality threshold are discarded and the system prompts a redo, Fig. 7 step 706, [0147]).
Consider claim 4, Khoury’100 discloses the segments vary in duration (segments creating by parsing, and segments processed with duration augmentation are considered to have varying durations, [0056], i.e. the durations must either vary among the segments with each other, or among the segments themselves before/after duration augmentation).
Consider claim 5, Khoury’100 discloses said step of calculating the decision score comprising combining the determined weights (weighted combination of scores, [0148]).
Consider claim 7, Khoury’100 discloses the instructions when read and executed by said processor, further cause said electronic device to determine the captured audio data is fraudulent when the decision score fails to satisfy the threshold value (determining that the input audio is a presentation attack using the threshold, [0079]).
Consider claim 8, Khoury’100 discloses the instructions when read and executed by said processor, further cause said electronic device to discard segments of inadequate quality (segments below quality threshold are discarded and the system prompts a redo, Fig. 7 step 706, [0147]).
Consider claim 9, Khoury’100 discloses the segments vary in duration (segments creating by parsing, and segments processed with duration augmentation are considered to have varying durations, [0056], i.e. the durations must either vary among the segments with each other, or among the segments themselves before/after duration augmentation).
Consider claim 10, Khoury’100 discloses the instructions when read and executed by said processor, further cause said electronic device to combine the determined weight to calculate the decision score (weighted combination of scores, [0148]).
Consider claim 12, Khoury’100 discloses the instructions when read and executed by said processor, further cause said electronic device to determine the captured audio data is fraudulent when the decision score fails to satisfy the threshold value (determining that the input audio is a presentation attack using the threshold, [0079]).
Consider claim 13, Khoury’100 discloses the instructions when read and executed by said processor, further cause said electronic device to discard segments of inadequate quality (segments below quality threshold are discarded and the system prompts a redo, Fig. 7 step 706, [0147]).
Consider claim 14, Khoury’100 discloses the segments vary in duration (segments creating by parsing, and segments processed with duration augmentation are considered to have varying durations, [0056], i.e. the durations must either vary among the segments with each other, or among the segments themselves before/after duration augmentation).
Consider claim 15, Khoury’100 discloses the instructions when read and executed by said processor, further cause said non-transitory computer-readable recording medium to perform the step of calculating the decision score by combining the determined weights (weighted combination of scores, [0148]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20210280171 Phatak discloses speaker-independent embedding for identification and verification from audio
US 20190228778 Lesso discloses speaker identification by fusing scores
US 20240355337 Altaf discloses speaker deepfake detection
US 20240363125 Khoury discloses an active voice liveness detection system
US 20170251014 Eisen discloses anti-replay systems for detecting likelihood of a replay attack
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jesse Pullias whose telephone number is 571/270-5135. The examiner can normally be reached on M-F 8:00 AM - 4:30 PM. The examiner’s fax number is 571/270-6135.
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, Andrew Flanders can be reached on 571/272-7516.
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.
/Jesse S Pullias/
Primary Examiner, Art Unit 2655 06/02/26
Prosecution Insights