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 Applicant’s submission filed on 2/19/2025 (with Apparent priority date of 3/01/2024). Claims 1-30 are pending of which claims 1, and 16 are independent. As such, claims 1-30 have been examined.
Specification
The disclosure is objected to because of the following informalities: In the Abstract, the term “phrase extraction layer” was used, However, in the specification, the term “phase extraction layer” was also used as well as “phase correction”. There appears to be some inconsistencies between the Abstract, drawings and the specification that should be thoroughly check for unless both phrases are meant to be used, as those two terms does not appear to be interchangeable.
Likewise in the specification, the terms “phrase” and “phase” are used throughout, it is not entirely clear which term the Applicant intended to use or if both, but both terms are also used to reference to reference designator 260 which is also reference to as “phase corrector” of fig. 2.
Appropriate correction is required.
Drawings
The drawings are objected to because in figure 7, in box 714, the term “phrase extraction layer” is used, but in the specification of the instant application, para 0004 and 0063, the term “phase extraction layer” is also used. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-30 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In in independent claims 1 and 16, “a phrase extraction layer” is recited, however, in the specification, “a phase extraction layer” is also referenced. It is not clear which term or both term is intended by the Applicant or if the Applicant is using the two terms interchangeably. There does not appear to be custom or Applicant defined terms that explicitly define either of the terms mentioned, therefore its not clear which term is the intended term, or if they can be used interchangeably. However, in standard dictionary, the term “phase” and “phrase” are not the same, or considered synonyms of one to another.
Potentially Allowable Subject Matter
Claims 1-30 would be potentially allowable if amended to overcome the pertinent rejections under section of the 112 rejections.
The following is a statement of reasons for the indication of potentially allowable subject matter:
With respect to Claim 1, The closest prior arts found during the search are as follows:
Caroselli (US 20230298612) discloses: 1. A multichannel neural frontend speech enhancement model for speech recognition, the speech enhancement model comprising: ([0004] One aspect of the present disclosure provides a multichannel neural frontend speech enhancement model for speech recognition)
a first pre-processor block configured to: receive, as input, ([0004] The speech cleaner receives, as input, a multichannel noisy input signal and a multichannel contextual noise signal, and generates, as output, a single channel cleaned input signal. The stack of self-attention blocks receives, as input, at an initial block of the stack of self-attention blocks, a stacked input including the single channel cleaned input signal output from the speech cleaner and a single channel noisy input signal, …)
the single channel cleaned input signal generated from a multichannel noisy input signal and a multichannel contextual noise signal; ([0004] The speech cleaner receives, as input, a multichannel noisy input signal and a multichannel contextual noise signal, and generates, as output, a single channel cleaned input signal.)
and generate, as output, ([0004] and generates, as output, from a final block of the stack of self-attention blocks, an un-masked output.)
a second pre-processor block configured to: receive, as input, ([0004] The masking layer receives, as input, the single channel noisy input signal)
and generate, as output, a([0004] receives, as input, the single channel noisy input signal and the un-masked output generated as output from the final block of the stack of self-attention blocks, and generates, as output, enhanced input speech features corresponding to a target utterance.)
a stack of self-attention blocks each having a multi-headed self attention mechanism, the stack of self-attention blocks configured to: ([0004] a stack of self-attention blocks each having a multi-headed self attention mechanism,)
receive, as input, at an initial block of the stack of self-attention blocks, ([0004] The stack of self-attention blocks receives, as input, at an initial block of the stack of self-attention blocks, a stacked input including the single channel cleaned input signal output from the speech cleaner and a single channel noisy input signal,)
a stacked input comprising the
and the ([0004] and a single channel noisy input signal,)
and generate, as output, from a final block of the stack of self-attention blocks, an un-masked output; ([0004] and generates, as output, from a final block of the stack of self-attention blocks, an un-masked output.)
a second masking layer configured to: receive, as input, the STFT coefficients for the single channel noisy input signal and the un-masked output generated as output from the final block of the stack of self-attention blocks; ([0050] The masking layer 240 is configured to receive, as input, the un-masked output 480 output by the self-attention blocks 400 of encoder 230, and the single channel 206a of the multichannel noisy input signal 202 and generate, as output the enhanced input speech features 250 corresponding to the target utterance 12.)
and generate, as output, a masked single channel noisy input signal; ([0050] generate, as output the enhanced input speech features 250 corresponding to the target utterance 12.)
and generate, as output, enhanced input speech features corresponding to a target utterance. ([0050] generate, as output the enhanced input speech features 250 corresponding to the target utterance 12.)
Applicant supplied reference (already of record) Caroselli, J., Narayanan, A., Howard, N., & O’Malley, T. (2023, June). Cleanformer: A multichannel array configuration-invariant neural enhancement frontend for asr in smart speakers. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE. – discloses generating a single channel cleaned STFT output from a multichannel noisy input and contextual noise by estimate the context before a keyword. However, it does not disclose the generating max value of an embedding dimension, it also silent with regard to second block for computing embedding dimension value for a raw single channel noisy signal.
Applicant supplied reference (already of record) Wang, Q., Muckenhirn, H., Wilson, K., Sridhar, P., Wu, Z., Hershey, J., ... & Moreno, I. L. (2018). Voicefilter: Targeted voice separation by speaker-conditioned spectrogram masking. arXiv preprint arXiv:1810.04826. – discloses: receive, as input, short-time Fourier transform (STFT) coefficients for a single channel cleaned input signal, the single channel cleaned input signal generated from a (see fig. 1, clean audio path)
a second pre-processor block configured to: receive, as input, STFT coefficients for a single channel noisy input signal; (see fig. 1, noisy audio path)
receive, as input, the STFT coefficients for the single channel cleaned input signal and the un-masked output generated as output from the ([Abstract] we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask.) Also see fig. 1.
and generate, as output, a masked single channel cleaned input signal; ([Abstract] we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask.) Also see fig. 1.
Wei US US 12567403 discloses: a stacked input comprising the maximum value of the embedding dimension of the (the global prosodic encoder 420 may employ a 2-D convolutional neural network (CNN) model to capture global prosodic signals at varying timescales using multiple convolution filters. The output from each filter may be max-pooled, stacked, and flattened, resulting in an output feature matrix V. The global prosodic encoder 420 may output the feature matrix V as global prosodic embedding data 422.)
Applicant supplied reference (already of record) Taghizadeh US 20220150661-discloses: a phase extraction layer ([0019] the processing circuitry is configured to extract phase information from one of the plurality of audio channels and to generate the output signal on the basis of the plurality of processed two-dimensional sub-arrays and the extracted phase information.)
Yao US 20230139642 discloses a semantic representation layer of candidate phrase classification model use to extract feature of candidate phrase in para 0102.
Xiong US 20210004439 discloses a neural key phrase extraction model that has a first layer to extract a word sequence from a document. See Abstract.
Accordingly, although the combination of prior art appears to disclose majority of the elements by individually teach bits and pieces of limitations of the claim, the prior art of record fails to explicitly teach or fairly suggest the invention in a reasonable combination as set forth in claim 1. Other independent claims 16, although different in statutory category, but contain similar limitations as claim 1, therefore also contains potentially allowable subject matter. Further dependent claims 2-15, and 17-30 inherit the potentially allowable subject matter from claims 1, and 16 respectively, and thus, also contain potentially allowable subject matter by virtue of their dependency.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Narayanan US 20230038982 discloses method for ASR using joint acoustic echo cancellation, speech enhancement and voice separation. See Abstract, and figs 1-6 for additional details.
Dushyant US 20230267944 method for optimizing a multi-channel input to single channel output system using short-time fourier transform (STFT). See Abstract, para 0025, 0027 and figs. 1a, 1b, 2a, 2b, 2c and 2d for additional details.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip H Lam whose telephone number is (571)272-1721. The examiner can normally be reached 9 AM-3 PM Pacific time.
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 on 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.
/PHILIP H LAM/ Examiner, Art Unit 2656
