DETAILED ACTION
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
The Response filed on 29 July 2026 has been correspondingly accepted and considered in the office action. Claims 1-18, 22 and 25 are pending. Claims 1, 12 and 22 are independent and amended. Dependent Claims 7 and 10 are also amended. Claims 19-21 and 23-24 are previously cancelled.
The objection to Claim 1 has been withdrawn in view of Applicant’s amendment to Claim 1 and persuasive arguments.
Response to Arguments
Claims 1-18, 22 and 25 stand rejected under 35 U.S.C. § 103. Applicant’s arguments with respect to Claims 1-18, 22 and 25 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
In order to expedite prosecution, and as to the material from the Specifications that are not in the Claim and are argued by the Applicant, please note Reynolds et al. ("Speaker Verification Using Adapted Gaussian Mixture Models," Digital Signal Processing 10 (2000), 19–41). For at least the supra provided reasons, Applicant's arguments have been fully considered but they are not persuasive.
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 (i.e., changing from AIA to pre-AIA ) 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, 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, 3-7, 9-10, 12, 14-18, 22 and 25 are rejected under 35 U.S.C. 103 as being unpatentable over Khoury et al. (US Pub 2021/0326421) in view of Reynolds et al. ("Speaker Verification Using Adapted Gaussian Mixture Models," Digital Signal Processing 10 (2000), 19–41).
Regarding claim 1,
Khoury discloses an apparatus comprising: interface circuitry; machine-readable instructions; and programmable circuitry to at least one of execute or instantiate the machine-readable instructions to (Khoury, par [014], "…a computer comprising a processor configured to: extract an inbound embedding for an inbound speaker by applying a machine-learning model on an inbound audio signal..."; Fig.1, par [075], "…a system 100 employing audio-processing machine-learning operations. The system 100 comprises an analytics system 101, a content system 110, and end-user devices 114..." ): calculate a sample embedding vector that characterizes a speaker based on a first audio signal (Fig.1, par [118], "…The analytics server 102 extracts embeddings from the audio signal using a neural network architecture (e.g., a deep neural network (DNN), a convolutional neural network (CNN)), Gaussian mixture models (GMM), or other machine learning methods. The analytics server 102 may represent the embeddings using x-vectors, CNN vectors, i-vectors, and the like...");
perform a first update of a personal embedding vector based on the sample embedding vector, the updated personal embedding vector to characterize the speaker based on a second audio signal and the first audio signal (par [054], "…If the similarity score exceeds the higher threshold, then the server verifies or authenticates the speaker. The server then adds the inbound embedding to the voiceprint and adds the inbound utterance to the speaker profile as a new utterance associated with the speaker..."; par [148], "…A strong embedding is an embedding that is very similar ( e.g., close with respect to a relative distance) to the voiceprint. The analytics server 102 updates the speaker cluster to include the embedding...the analytics server 102 may update the voiceprint by taking a weighted average of the embeddings...");
Khoury does not explicitly disclose updating voiceprint with a universal embedding vector.
Reynolds, in the analogous field of speaker verification and speaker-model adaptation, discloses perform a second update of the personal embedding vector by combining the updated personal embedding vector with a universal embedding vector (Reynolds, 2. Likelihood Ratio Detector, "…The main advantage of this approach is that a single speaker-independent model can be trained once for a particular task and then used for all hypothesized speakers in that task...It is also possible to use multiple background models tailored to specific sets of speakers..."; 3.3. Universal Background Model, "…The UBM is a large GMM trained to represent the speaker-independent distribution of features..."; 3.4. Adaptation of Speaker Model, "…the basic idea in the adaptation approach is to derive the speaker’s model by updating the well-trained parameters in the UBM via adaptation...", see Equations 11-12 and the adaptation coefficients controlling the balance between old and new estimates).
Therefore, it would have been obvious to one of ordinary skill in the art, before effective filing date of the claimed invention, to have modified a passively updated voiceprint of Khoury with the interpolation toward a universal background model of Reynolds, with a reasonable expectation of success, to yield the predictable result of a speaker model that remains robust to limited data (Reynolds, 3.4. Adaptation of Speaker Model).
Regarding claim 3,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein the apparatus corresponds to a first user and a second user, and the apparatus further includes: identifier circuitry to identify, based on the personal embedding vector after the second update, the speaker as the first user or the second user (Khoury, Fig.1, par [087], "…the subscriber could represent a household and members of a family and/or guests who access the services of the content system 110 using the end-user devices 114..."; par [172], "…the analytics server 102 may determine the identity of a user interacting with the end-user device 114 by comparing the similarity of the extracted embedding to embeddings/voiceprints stored in the analytics database 104....").
Regarding claim 4,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein the first audio signal is not obtained as part of an enrollment process (Khoury, par [045], "…Passive enrollment does not require user prompts, though some implementations employ hybrid approaches (e.g., active and passive)...").
Regarding claim 5,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein to perform the first update of the personal embedding vector, the programmable circuitry is to: determine a ratio; and combine a first vector and a second vector, the first vector based on a previous version of the personal embedding vector and the ratio, the second vector based on the sample embedding vector and the ratio (Khoury, par [148], "…The analytics server 102 updates the speaker cluster to include the embedding...the analytics server 102 may update the voiceprint by taking a weighted average of the embeddings..."; Reynolds, 3.4. Adaptation of Speaker Model, "…the basic idea in the adaptation approach is to derive the speaker’s model by updating the well-trained parameters in the UBM via adaptation...", see Equations 11-13 show weighting new and old estimates by the adaptation coefficients α and (1- α). The adaptation coefficients control the balance between old and new estimates).
Regarding claim 6,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein: the speaker is a first speaker; the sample embedding vector is a second sample embedding vector corresponding to the first audio signal; and the programmable circuitry is to: identify an unknown speaker in a third audio signal; calculate a third sample embedding vector based on the third audio signal; and determine whether to perform an additional update of the personal embedding vector with the third sample embedding vector, the determination based on a distance calculation between the personal embedding vector and the third sample embedding vector (Khoury, par [013], "…a similarity score based upon a distance between the inbound embedding and a voiceprint stored in speaker profile in a speaker profile database..."; Fig.3, par [214], "…if the server determines that the maximum similarity score fails one or more thresholds, the server determines that the speaker is likely a new unknown user 331..."; par [146], "…Weak embeddings lack enough similarity with the corresponding voiceprint for immediately characterizing the weak embedding as part of the particular speaker cluster...").
Regarding claim 7,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein to perform the second update of the personal embedding vector, the programmable circuitry is to: determine a ratio; and combine a first vector and a second vector, the first vector based on the personal embedding vector after the first update and the ratio, the second vector based on the universal embedding vector and the ratio (Reynolds, 3.4. Adaptation of Speaker Model, Eq. 12: the speaker-dependent vector is scaled by α and UBM mean by (1- α); "...we use a single adaptation coefficient for all parameters...with a relevance factor of r=16...").
Regarding claim 9,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein the second audio signal is obtained before the first audio signal (Khoury, par [049], "…perform continuous enrollment of, and periodic updates to, speaker profiles and speaker voiceprints to avoid staleness...").
Regarding claim 10,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein the universal embedding vector characterizes human voice (Reynolds, 2. Likelihood Ratio Detector, "…It is also possible to use multiple background models tailored to specific sets of speakers..."; 3.3. Universal Background Model, "…The UBM is a large GMM trained to represent the speaker-independent distribution of features...");
Claim 12 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 1 and is rejected under similar rationale. Additionally,
Khoury discloses a non-transitory machine-readable storage medium comprising instructions to cause programmable circuitry to (Khoury, par [0424], "…the functions may be stored as one or more instructions or code on a non-transitory computer-readable or processor-readable storage medium...")
...
Rationale for combination is similar to that provided for Claim 1.
Claim 14 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 3 and is rejected under similar rationale.
Claim 15 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 4 and is rejected under similar rationale.
Claim 16 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 5 and is rejected under similar rationale.
Claim 17 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 6 and is rejected under similar rationale.
Claim 18 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 7 and is rejected under similar rationale.
Claim 22 is a method claim with limitations similar to the limitations of Claim 1 and is rejected under similar rationale. Rationale for combination is similar to that provided for Claim 1.
Claim 25 is a method claim with limitations similar to the limitations of Claim 4 and is rejected under similar rationale.
Claims 2 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Khoury in view of Reynolds further in view of Cutler (US Pub 2023/0421702).
Regarding claim 2,
Khoury in view of Reynolds discloses the apparatus of claim 1, wherein the first audio signal includes audio from the speaker and parasitic noise (Khoury, par [116], "…The analytics server 102 performs audio event detection or other voice activity detection to differentiate between background noise, silence, and speakers in the audio signal...") but does not explicitly disclose the dynamic noise suppression circuitry based on the personal embedding vector.
However, Cutler, in the analogous field of call audio enhancement, discloses the apparatus further includes: dynamic noise suppression circuitry to output, based on the personal embedding vector after the second update, main speaker audio that includes the speaker but not the parasitic noise (Cutler, par [090], "… a given speaker's microphone might pick up other human voices, background noise (e.g., an HVAC fan, barking dog, etc.), room reverberation..."; Fig.5, par[052], "…The embedding can be employed by personalized enhancement models such as echo cancellation model 508, noise suppression model 510, and/or de-reverberation model 512 to suppress sounds other than those made by the user's voice speaking into microphone 502…"); and
transceiver circuitry to transmit the main speaker audio (Cutler, Fig. 5, par [053], "…an encoder 518 can encode the resulting sound signal for transmission over network 150...").
Therefore, it would have been obvious to one of ordinary skill in the art, before effective filing date of the claimed invention, to have supplied the personal embedding of Khoury in view of Reynolds (Khoury-Reynolds, hereinafter) to Cutler's embedding-conditioned noise suppression, with a reasonable expectation of success, to yield the predictable result of transmitted main-speaker audio with other voices and noise suppressed (Cutler, Background, Fig.5).
Claim 13 is a non-transitory machine-readable storage medium claim with limitations similar to the limitations of Claim 2 and is rejected under similar rationale.
Rationale for combination is similar to that provided for Claim 2.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Khoury in view of Reynolds further in view of Yu et al. (US Pub 2014/0257803).
Regarding claim 8,
Khoury in view of Reynolds discloses the apparatus of claim 7 but does not explicitly disclose the ratio change over subsequent iterations.
Yu, in the analogous field of speaker adaptation of speech-recognition model, discloses wherein the programmable circuitry is to change the ratio over subsequent iterations so that a magnitude of the first vector increases and a magnitude of the second vector decreases (par [032], "…As more speech data is received from the user 104, a value of the regularization weight selected by the adapter component 114 can decrease..."; par [035], "…the adapter component 114 can adapt parameters of the DNN 106 after each use of the recognition system 102...the adapter component 114 can incrementally adapt a DNN over time...").
Therefore, it would have been obvious to one of ordinary skill in the art, before effective filing date of the claimed invention, to have applied the interpolation ratio of Reynold to Yu's regularization weight, with a reasonable expectation of success, to yield the predictable result of a personal embedding that is stable when data are scarce and increasingly speaker-specific over subsequent iterations (Yu, Background, par [035]).
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Khoury in view of Reynolds further in view of Moon et al. (US Pub 2020/0286491).
Regarding claim 11,
Khoury in view of Reynolds discloses the apparatus of claim 1. Moon, in the analogous field of speaker embedding and verification, discloses a device whose CPU and digital signal processors execute stored instructions for extracting and updating speaker embedding.
Moon discloses wherein the programmable circuitry includes one or more of:
at least one of a central processor unit, a graphics processor unit, or a digital signal processor (Moon, Fig.10, par [152], "…the device 1000 includes a processor 1006 (e.g., a central processing unit (CPU)). The device 1000 may include one or more additional processors 1010 (e.g., one or more digital signal processors (DSPs))…"),
the at least one of the central processor unit, the graphics processor unit, or the digital signal processor having control circuitry to control data movement within the programmable circuitry, arithmetic and logic circuitry to perform one or more first operations corresponding to machine-readable data (Moon, Fig.10, par [155], "…The memory 1032 may include instructions 1060 executable by the processor 1006, the processors 1010..."), and
one or more registers to store a result of the one or more first operations, the machine-readable data in the apparatus; a Field Programmable Gate Array (FPGA), the FPGA including logic gate circuitry, a plurality of configurable interconnections, and storage circuitry, the logic gate circuitry and the plurality of the configurable interconnections to perform one or more second operations, the storage circuitry to store a result of the one or more second operations; or application Specific Integrated Circuitry (ASIC) including logic gate circuitry to perform one or more third operations (Moon, Fig.1, par [028], "…implemented using hardware (e.g., a field programmable gate array (FPGA) device, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a controller, etc.), software (e.g., instructions executable by a processor), or any combination thereof...");
Therefore, it would have been obvious to one of ordinary skill in the art, before effective filing date of the claimed invention, to have executed embedding update of Khoury-Reynolds on Moon's device, whose CPU and DSPs run stored speaker-verification instruction, with a reasonable expectation of success, to yield the predictable result of on-device updating using known processor hardware (Moon, Background, Fig.10, paras [152-158]).
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 JANGWOEN LEE whose telephone number is (703)756-5597. The examiner can normally be reached Monday-Friday 8:00 am - 5:00 pm ET.
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, BHAVESH MEHTA can be reached at (571)272-7453. 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.
/JANGWOEN LEE/Examiner, Art Unit 2656
/BHAVESH M MEHTA/Supervisory Patent Examiner, Art Unit 2656
