Prosecution Insights
Last updated: November 12, 2026
Application No. 18/937,161

METHODS AND SYSTEMS FOR ENHANCING THE DETECTION OF FRAUDULENT AUDIO DATA

Final Rejection §101§103
Filed
Nov 05, 2024
Examiner
PULLIAS, JESSE SCOTT
Art Unit
2655
Tech Center
2600 — Communications
Assignee
Daon Technology
OA Round
2 (Final)
82%
Grant Probability
Favorable
3-4
OA Rounds
95%
With Interview

Examiner Intelligence

Grants 82% — above average
82%
Career Allowance Rate
889 granted / 1079 resolved
+20.4% vs TC avg
Moderate +13% lift
Without
With
+12.8%
Interview Lift
resolved cases with interview
Typical timeline
Avg Prosecution
29 currently pending
Career history
1123
Total Applications
across all art units

Office Action

§101 §103
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 correspondence 08/26/26 regarding application 18/937,161, in which claims 1, 3, 4, 6, 8, 9, 11, 13, and 14 were amended, claims 5, 10, and 15 were cancelled, and new claims 16-18 were added. Claims 1-4, 6-9, 11-14, and 16-18 are pending in the application and have been considered. Response to Arguments The examiner has reviewed the originally filed specification and agrees with Applicant on page 8 that no new matter was introduced via the amendments to claims 1, 3, 4, 6, 8, 9, 11, 13, and 14 and addition of new claims 16-18. Applicant’s arguments on pages 8-12 regarding the 35 U.S.C. 101 rejections of independent claims 1, 6, and 11 have been considered but are not persuasive. The examiner agrees with Applicant on pages 8-9 that the claims pass Step 1 of the subject matter eligibility test (i.e. the claims are directed to a machine, process, or manufacture). The examiner disagrees with Applicant on page 9 that the claims pass Step 2A prong 1. Applicant argues that the claims pass this prong because biometric verification transactions cannot be performed in the mind, so the claims do not recite a mental process. In response, it is noted that the claims as presently worded are not directed to biometric verification transactions in any technical sense such that the claimed techniques necessarily have to be performed on a computer and rule out performance in the mind. The claims are directed to performing a series of determinations, calculations, and comparisons all of which can be performed in the mind for the reasons described in the below 35 U.S.C. 101 rejection. It is generally noted that the abstract concept of determining whether audio is genuine can be performed by a human listener making a determination. For example, a cell phone answerer receiving a call from an unknown number might answer and mentally determine whether the voice on the other end appears to be authentically human or machine generated. This is nothing more than a mental judgement in the absence of some sort of audio processing that would require use of a computer. Applicant next argues that the claims pass Step 2A prong 2 because the claims allegedly contain additional elements that amount to a practical application that is significantly more than the judicial exception which improves the technology in the field of biometric authentication. The examiner respectfully disagrees because the claimed series of determinations, calculations, and comparisons is never actually applied to any biometric authentication in the technical sense as claimed. The claims do not, for example, grant a user access to a system based on the results of the authentication. The closest that claim 1, for example, comes to any biometric authentication is the final step of “determining the captured audio is genuine”. This is not considered biometric authentication in the technical sense, however, because a human listener can listen to audio of a person speaking and make a mental judgement of whether the audio sounds authentic or not, and the claimed audio processing steps, with the exception of the determining “by a trained machine learning model operated by the electronic device”, can all be performed mentally or with a pen and paper as explained below. The mere inclusion of a generic “trained machine learning model” does not amount to significantly more for the reasons explained below as well. Applicant’s arguments on pages 12-16 regarding the 35 U.S.C. 103 rejections of independent claims 1, 6, and 11 based on Khoury’100 and Khoury’046 have been considered but are not persuasive. First, Applicant argues that Khoury’100 does not disclose dividing the audio data into segments, wherein the audio segments vary in duration. The examiner respectfully disagrees. Applicant seems to argue that augmenting the duration of an audio segment increases the size of a segment, which somehow does not mean that the segments have varying durations. (See page 13). However, if a segment duration has been increased, it is longer than the old duration, and thus varies from the old duration. Moreover, Khoury’100 further describes parsing audio data into speech segments and filtering out non-speech, see [0060]. This by itself is fairly considered to disclose dividing the audio data into segments, wherein the audio segments vary in duration, since as those skilled in the field of speech processing, and anyone who has ever viewed an audio waveform of speech would have been aware, speech segments with periods of non-speech in between naturally vary by duration. Second, Applicant argues that Khoury’100 does not disclose calculating a decision score by combining the determined weights, allegedly because the generating a weighted fused liveness score is not the same as combining weights to calculate a liveness score. The examiner respectfully disagrees and maintains that “weighted combination” expressly described in Khoury’100 applies a weight to the passive liveness score to determine a final liveness score, and the weighted “combination” of scores, expressly corresponds to the claimed calculating a decision score by combining the determined weights. See Khoury’100, [0148]. 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 1-3, 6-8, and 11-13 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, wherein the audio segments vary in duration; 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 by combining the determined weights; 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, wherein the audio segments vary in duration”, 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, wherein the audio segments vary in duration” in the context of this claim encompasses mentally dividing transcript into segments corresponding to audio segments having varying duration 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 by combining the determined weights” 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 by combining the determined weights” 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 by mentally combining the determined weights. 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 2-3 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 2-3 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 “determining acoustic cues for each segment; calculating an acoustic cue score for each segment; and determining the quality control vector for each segment based on the acoustic cue scores calculated for the respective segment” which could be performed by mentally determining whether a segment is loud enough to clearly hear, mentally calculating a score based on the perceived loudness, and mentally determining a quality control vector based on the scores for the audio. In sum, claims 2-3 depend from claim 1 and further recite mental processes as explained above. None of the additional limitations recited in claims 2-3 amount to anything more than the same or a similar abstract idea as recited in claim 1. Nor do any limitations in claims 2-3 (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 2-3 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 7-8 depend from claim 6, do not remedy any of the deficiencies of claim 6, and correspond to the subject matter of claims 2-3 above, and therefore are rejected on the same grounds as claims 2-3 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 12-13 depend from claim 11, do not remedy any of the deficiencies of claim 11, and correspond to the subject matter of claims 2-3 above, and therefore are rejected on the same grounds as claims 2-3 and 11 above. Eligible Claims Claims 4, 9, and 14 require calculating acoustic cues of: a signal-to-noise ratio; a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio, which cannot be calculated mentally or with a pen and paper in any practical sense. Claims 16-18 depend on intervening claims 4, 9, and 14 and recite the eligible subject matter of these parent intervening claims; these claims additionally recite further audio processing subject matter that cannot be practically performed mentally or with a pen and paper, and are additionally eligible for that reason. 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 1-3, 6-8, and 11-13 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]), wherein the audio segments vary in duration (segments creating by parsing, which parses the speech portions away from the non-speech portions of the audio signal, [0060], 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); 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 (a weighted combination applies a weight to the passive liveness score to determine a final liveness score, [0148]); calculating a decision score by combining the determined weights (weighted combination of scores, [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); dividing the audio data into segments (parsing and segmenting the audio signal into frames or segments, [0056]), wherein the audio segments vary in duration (segments creating by parsing, which parses the speech portions away from the non-speech portions of the audio signal, [0060], 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); 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 (a weighted combination applies a weight to the passive liveness score to determine a final liveness score, [0148]); calculate a decision score by combining the determined weights (weighted combination of scores, [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]), wherein the audio segments vary in duration (segments creating by parsing, which parses the speech portions away from the non-speech portions of the audio signal, [0060], 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); 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 (a weighted combination applies a weight to the passive liveness score to determine a final liveness score, [0148]); calculating a decision score by combining the determined weights (weighted combination of scores, [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 said step of determining a quality control vector for each segment comprising: determining acoustic cues for each segment (calculating acoustic parameters, e.g. SNR, T60, etc., Fig 5A, [0129]-[0130], for audio segments creating by parsing, [0060]); calculating an acoustic cue score for each segment (computing the acoustic parameters, [0129-0132]); and determining the quality control vector for each segment based on the acoustic cue scores calculated for the respective segment (quality estimation scoring layer generates a speech quality score as an integrated value of the acoustic parameters, Fig 5A, [0130]). 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 for determining a quality control vector for each segment when read and executed by said processor, further cause said electronic device to determine acoustic cues for each segment (calculating acoustic parameters, e.g. SNR, T60, etc., Fig 5A, [0129]-[0130], for audio segments creating by parsing, [0060]); calculate an acoustic cue score for each segment (computing the acoustic parameters, [0129-0132]); and determine the quality control vector for each segment based on the acoustic cue scores calculated for the respective segment (quality estimation scoring layer generates a speech quality score as an integrated value of the acoustic parameters, Fig 5A, [0130]). 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 for determining a quality control vector for each segment when read and executed by said processor, further cause said electronic device to perform steps comprising: determining acoustic cues for each segment (calculating acoustic parameters, e.g. SNR, T60, etc., Fig 5A, [0129]-[0130], for audio segments creating by parsing, [0060]); calculating an acoustic cue score for each segment (computing the acoustic parameters, [0129-0132]); and determining the quality control vector for each segment based on the acoustic cue scores calculated for the respective segment (quality estimation scoring layer generates a speech quality score as an integrated value of the acoustic parameters, Fig 5A, [0130]). Claims 4, 9, 14, and 16-18 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, in further view of Serra et al. (US 20230245674). Consider claim 4, Khoury’100 discloses the acoustic cues comprise: a signal-to-noise ratio (SNR, [0081]). Khoury’100 and Khoury’046 do not specifically mention: a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio. Serra discloses a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio (PESQ, STOI, SISDR, [0027]). 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 and Khoury’046 such that the acoustic cues comprise a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio in order to improve objective and automatic speech quality assessment, predictably reducing effort, time, and cost of evaluating speech quality, as suggested by Serra ([0003]). The references cited are analogous art in the same field of speech processing. Consider claim 9, Khoury’100 discloses the acoustic cues comprise: a signal-to-noise ratio (SNR, [0081]). Khoury’100 and Khoury’046 do not specifically mention: a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio. Serra discloses a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio (PESQ, STOI, SISDR, [0027]). 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 and Khoury’046 such that the acoustic cues comprise a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio for reasons similar to those for claim 4. Consider claim 14, Khoury’100 discloses the acoustic cues comprise: a signal-to-noise ratio (SNR, [0081]). Khoury’100 and Khoury’046 do not specifically mention: a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio. Serra discloses a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio (PESQ, STOI, SISDR, [0027]). 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 and Khoury’046 such that the acoustic cues comprise a Perceptual Evaluation of Speech Quality; a short-time objective intelligibility; and a Scale-Invariant Signal-to-Distortion Ratio for reasons similar to those for claim 4. Consider claim 16, Khoury’100 discloses calculating an acoustic cue for each segment further comprising: calculating the acoustic cue score for the signal-to-noise ratio using signal processing techniques (calculating acoustic parameters including SNR, Fig 5A, [0129]-[0130], using audio-processing software, i.e. signal processing techniques, [0053]). Khoury’100 and Khoury’046 do not specifically mention calculating the acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model. Serra discloses calculating an acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model (training the ML model to predict PESQ, STOI, and SISDR, [0105-0107], [0113]). 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 and Khoury’046 by calculating the acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model for reasons similar to those for claim 4. Consider claim 17, Khoury’100 discloses the instructions for calculating an acoustic cue for each segment when read and executed by said processor, further cause said electronic device to: calculate the acoustic cue score for the signal-to-noise ratio using signal processing techniques (calculating acoustic parameters including SNR, Fig 5A, [0129]-[0130], using audio-processing software, i.e. signal processing techniques, [0053]). Khoury’100 and Khoury’046 do not specifically mention calculating the acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model. Serra discloses calculating an acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model (training the ML model to predict PESQ, STOI, and SISDR, [0105-0107], [0113]). 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 and Khoury’046 by calculating the acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model for reasons similar to those for claim 4. Consider claim 18, Khoury’100 discloses the instructions when read and executed by said processor, further cause said non- transitory computer-readable recording medium to perform the steps of: calculating the acoustic cue score for the signal-to-noise ratio using signal processing techniques (calculating acoustic parameters including SNR, Fig 5A, [0129]-[0130], using audio-processing software, i.e. signal processing techniques, [0053]). Khoury’100 and Khoury’046 do not specifically mention calculating the acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model. Serra discloses calculating an acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model (training the ML model to predict PESQ, STOI, and SISDR, [0105-0107], [0113]). 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 and Khoury’046 by calculating the acoustic cue score for the Perceptual Evaluation of Speech Quality cue, the short-time objective intelligibility cue, and the Scale-Invariant Signal-to-Distortion Ratio cue using a trained machine learning model for reasons similar to those for claim 4. Conclusion Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a). A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action. 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 10/14/26
Read full office action

Prosecution Timeline

Nov 05, 2024
Application Filed
Jun 05, 2026
Non-Final Rejection mailed — §101, §103
Aug 26, 2026
Response Filed
Oct 16, 2026
Final Rejection mailed — §101, §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12783795
COMPUTER METHOD AND SYSTEM FOR PARSING HUMAN DIALOUGE
3y 7m to grant Granted Nov 03, 2026
Patent 12749483
SYSTEM, APPARATUS, AND METHOD FOR PROCESSING NATURAL LANGUAGE, AND NON-TRANSITORY COMPUTER READABLE RECORDING MEDIUM
3y 2m to grant Granted Sep 29, 2026
Patent 12738286
POST-PROCESSOR, AUDIO DECODER AND RELATED METHODS FOR ENHANCING TRANSIENT PROCESSING
6y 3m to grant Granted Sep 15, 2026
Patent 12730980
REAL-TIME ADAPTATION OF MACHINE LEARNING MODELS USING LARGE LANGUAGE MODELS
2y 9m to grant Granted Sep 08, 2026
Patent 12694234
IMAGE-BASED TEXT TRANSLATION AND PRESENTATION
3y 10m to grant Granted Jul 28, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
82%
Grant Probability
95%
With Interview (+12.8%)
Moderate
PTA Risk
Based on 1079 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month