DETAILED ACTION
This is responsive to the application filed 03 October 2024.
Claims 1-20 are pending and considered below.
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 .
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-20 are rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of U.S. Patent No. 12,131,745. Although the claims at issue are not identical, they are not patentably distinct from each other because claims 1-20 of U.S. Patent No. 12,131,745 anticipate the currently pending claims.
The parent claims include all of the limitations of the instant application claims, respectively (see example in table below). The parent claims also include additional limitations. Hence, the instant application claims are generic to the species of invention covered by the respective parent claims. As such, the instant application claims are anticipated by the parent claims and are therefore not patentably distinct therefrom. (See Eli Lilly and Co. v. Barr Laboratories Inc., 58 USPQ2D 1869, "a later genus claim limitation is anticipated by, and therefore not patentably distinct from, an earlier species claim", In re Goodman, 29 USPQ2d 2010, "Thus, the generic invention is 'anticipated' by the species of the patented invention" and the instant “application claims are generic to species of invention covered by the patent claim, and since without terminal disclaimer, extant species claims preclude issuance of generic application claims”).
Further, it is well settled that the omission of an element/step and its function is an obvious expedient if the remaining elements perform the same function as before. In re Karlson, 136 USPQ 184 (CCPA 1963). Also note Ex parte Rainu, 168 USPQ 375 (Bd. App. 1969). Omission of a reference element or step whose function is not needed would be obvious to one of ordinary skill in the art.
Current claims
Claims of U.S. Patent No. 12,131,745
1. A system, comprising an audio interface, memory having instructions stored thereon, and one or more processors coupled to the memory and configured to execute the instructions to:
generate from input audio data obtained via the audio interface first phonetic embedding vectors for phonetic content representing a source accent;
apply a trained neural network to the first phonetic embedding vectors to generate second phonetic embedding vectors corresponding to first phonetic characteristics of speech data in a target accent;
determine a differentiable alignment based on the first and second phonetic embedding vectors; and
align the speech data to the phonetic content based on the determined differentiable alignment to generate output audio data representing the target accent.
2. The system of claim 1, wherein the first phonetic embedding vectors represent second phonetic characteristics of input speech in the input audio data in a numerical format and encode one or more of phonetic features, patterns, phonemes, pronunciation, intonation, speech sounds, or phonetic units present in the input speech.
3. The system of claim 1, wherein the neural network: is trained to learn a mapping between the first phonetic embedding vectors and the second phonetic embedding vectors using a labeled dataset comprising paired samples of course accent phonetic embedding vectors and corresponding target accent phonetic embedding vectors; and comprises an encoder layer configured to encode the first phonetic embedding vectors into a latent representation and a decoder layer configured to decode the latent representation to generate the second phonetic embedding vectors.
4. The system of claim 1, wherein the one or more processors are further configured to execute the instructions to determine the differentiable alignment by jointly maximizing a cosine distance between the first phonetic embedding vectors and the second phonetic embedding vectors.
5. The system of claim 4, wherein the one or more processors are further configured to execute the instructions to, in order to determine the cosine distance: normalize the first and second phonetic embedding vectors by scaling the first and second phonetic embedding vectors to have a magnitude of one and preserving a relative direction of the first and second phonetic embedding vectors; and generate a dot product of the normalized first and second phonetic embedding vectors.
6. The system of claim 4, wherein the one or more processors are further configured to execute the instructions to apply a gradient-based optimization algorithm to optimize the joint maximization of the cosine distance.
7. The system of claim 1, wherein the one or more processors are further configured to execute the instructions to, in order to generate the output audio data, one or more of: align first frames of the speech data with corresponding second frames of the phonetic content; apply one or more of prosody modeling, intonation adjustment, or accent-specific acoustic modeling techniques; or adjust a speech rate, pitch, or gender, wherein the output audio data preserves linguistic content of the input audio data.
1. An accent conversion system, comprising an audio interface, memory having instructions stored thereon, and one or more processors coupled to the memory and configured to execute the instructions to:
obtain input audio data via the audio interface;
generate from the input audio data first phonetic embedding vectors for phonetic content representing a source accent;
apply a trained accent conversion neural network to the first phonetic embedding vectors to generate second phonetic embedding vectors corresponding to first phonetic characteristics of speech data in a target accent;
determine a differentiable alignment by jointly maximizing a cosine distance between the first phonetic embedding vectors and the second phonetic embedding vectors; and
align the speech data to the phonetic content based on the differentiable alignment to generate and provide output audio data corresponding to the aligned speech data and representing the target accent.
2. The accent conversion system of claim 1, wherein the first phonetic embedding vectors represent second phonetic characteristics of input speech in the input audio data in a numerical format and encode one or more of phonetic features, patterns, phonemes, pronunciation, intonation, speech sounds, or phonetic units present in the input speech.
3. The accent conversion system of claim 1, wherein the accent conversion neural network: is trained to learn a mapping between the first phonetic embedding vectors and the second phonetic embedding vectors using a labeled dataset comprising paired samples of course accent phonetic embedding vectors and corresponding target accent phonetic embedding vectors; and comprises an encoder layer configured to encode the first phonetic embedding vectors into a latent representation and a decoder layer configured to decode the latent representation to generate the second phonetic embedding vectors.
(see claim 1 above)
4. The accent conversion system of claim 1, wherein the one or more processors are further configured to execute the instructions to, in order to determine the cosine distance: normalize the first and second phonetic embedding vectors by scaling the first and second phonetic embedding vectors to have a magnitude of one and preserving a relative direction of the first and second phonetic embedding vectors; and generate a dot product of the normalized first and second phonetic embedding vectors.
6. The accent conversion system of claim 1, wherein the one or more processors are further configured to execute the instructions to apply a gradient-based optimization algorithm to optimize the joint maximization of the cosine distance.
5. The accent conversion system of claim 1, wherein the one or more processors are further configured to execute the instructions to, in order to generate the output audio data, one or more of align first frames of the speech data with corresponding second frames of the phonetic content, apply one or more of prosody modeling, intonation adjustment, or accent-specific acoustic modeling techniques, or adjust a speech rate, pitch, or gender, wherein the output audio data preserves linguistic content of the input audio data.
Claims 1, 4-6, 8, 11-13, 15 and 17-19 are provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-20 of copending Application No. 19/397,799 (reference application). Although the claims at issue are not identical, they are not patentably distinct from each other because claims 1-20 of copending Application No. 19/397,799 anticipate the currently pending claims 1, 4-6, 8, 11-13, 15 and 17-19 (see examples in table below).
Current claims
Claims copending Application No. 19/397,799
1. A system, comprising an audio interface, memory having instructions stored thereon, and one or more processors coupled to the memory and configured to execute the instructions to:
generate from input audio data obtained via the audio interface first phonetic embedding vectors for phonetic content representing a source accent;
apply a trained neural network to the first phonetic embedding vectors to generate second phonetic embedding vectors corresponding to first phonetic characteristics of speech data in a target accent;
determine a differentiable alignment based on the first and second phonetic embedding vectors; and
align the speech data to the phonetic content based on the determined differentiable alignment to generate output audio data representing the target accent.
4. The system of claim 1, wherein the one or more processors are further configured to execute the instructions to determine the differentiable alignment by jointly maximizing a cosine distance between the first phonetic embedding vectors and the second phonetic embedding vectors.
5. The system of claim 4, wherein the one or more processors are further configured to execute the instructions to, in order to determine the cosine distance: normalize the first and second phonetic embedding vectors by scaling the first and second phonetic embedding vectors to have a magnitude of one and preserving a relative direction of the first and second phonetic embedding vectors; and generate a dot product of the normalized first and second phonetic embedding vectors.
6. The system of claim 4, wherein the one or more processors are further configured to execute the instructions to apply a gradient-based optimization algorithm to optimize the joint maximization of the cosine distance.
1. A system, comprising an audio interface, a communication interface, memory having instructions stored thereon, and one or more processors coupled to the memory and configured to execute the instructions to:
receive output audio data representing a target accent and comprising speech data aligned to phonetic content representing a source accent based on a differentiable alignment determined based on first and second phonetic embedded vectors, wherein: the first phonetic embedding vectors are generated from input audio data and are for the phonetic content; and the second embedding vectors are generated based on an application of a trained neural network to the first phonetic embedding vectors and correspond to first phonetic characteristics of speech data in the target accent;
store the output audio data in the memory; and output the output audio data from the memory and via the audio interface.
4. The system of claim 1, wherein the differentiable alignment is determined by jointly maximizing a cosine distance between the first phonetic embedding vectors and the second phonetic embedding vectors.
5. The system of claim 4, wherein the cosine distance is determined based on a generated dot product of a normalization of the first and second phonetic embedding vectors based on a scaling of the first and second phonetic embedding vectors to have a magnitude of one and a preservation of a relative direction of the first and second phonetic embedding vectors.
6. The system of claim 4, wherein the joint maximization of the cosine distance is optimized based on an application of a gradient-based optimization algorithm.
This is a provisional nonstatutory double patenting rejection because the patentably indistinct claims have not in fact been patented.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 8-9, 14-16 and 20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Keshet et al. (US 2024/0304200).
Claim 8:
Keshet discloses a method, comprising:
obtaining from input audio data phonetic embedding vectors for phonetic content representing a source accent (“the speech may be analyzed to generate a representation and/or embedding of voice characteristics of the speaker”, [0060], see also “voice analysis module 140 may analyze speech 20 to calculate a feature vector representation 140A (X)”, [0126], see [0159] for accent, see also Fig. 6, item 140A);
applying a trained machine learning model to the phonetic embedding vectors to generate transformed phonetic embedding vectors corresponding to phonetic characteristics of speech data in a target accent (“apply ML model 170 on the extracted portion … of the recorded speech, to generate a feature vector representation 170A”, [0130], see [0159] for accent, see also Fig. 6, items 170 and 170A);
determining an alignment (cosine distance value) based on the phonetic embedding vectors and the transformed phonetic embedding vectors (“calculate a cosine distance value, representing a cosine distance between one or more phoneme embeddings (PEy) of feature vector representation … and one or more phoneme embeddings (PE) corresponding to extracted section”, [0147]); and
aligning (minimizing a value of the weighted loss function) the speech data to the phonetic content based on the determined alignment to generate output audio data representing the target accent (“calculate the weighted loss function (e.g., weighted by λ.sub.5, λ.sub.5), further based on the calculated cosine distance values … and may train ML model 170 to generate the modified version 170A of the first portion of recorded speech by minimizing a value of the weighted loss function as elaborated above”, [0148], see also generating output in [0135]).
Claim 9:
Keshet discloses Keshet discloses the method of claim 8, wherein the phonetic embedding vectors represent other phonetic characteristics of input speech in the input audio data in a numerical format and encode one or more of phonetic features, patterns, phonemes, pronunciation, intonation, speech sounds, or phonetic units present in the input speech ([0126]).
Claim 14:
Keshet discloses the method of claim 8, further comprising, in order to generate the output audio data, one or more of: aligning first frames of the speech data with corresponding second frames of the phonetic content; applying one or more of prosody modeling, intonation adjustment, or accent-specific acoustic modeling techniques; or adjusting a speech rate, pitch, or gender, wherein the output audio data preserves linguistic content of the input audio data (“the present invention provides for real-time, automated re-synthesis of a speaker's speech, to correct misarticulation and/or mispronunciation of a word, words, a stream of words and/or one or more utterances (e.g., one or more phonemes), in a way which preserves characteristics of the original speech, including, but not limited to, perceived speaker voice and identity, naturalness, intonation, and/or rhythm”, [0058], note intonation for corrected word is adjusted to preserve characteristics of original speech, see also [0159]).
Claims 15-16 and 20:
Keshet ([0051] and [0170]) discloses a non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of process claims 8-9 and 14 as shown above.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Keshet et al. (US 2024/0304200) in view of Rafii (US 10,997,970).
Claim 10:
Keshet discloses the method of claim 8, but does not explicitly disclose wherein the machine learning model is trained to learn a mapping between the phonetic embedding vectors and the transformed phonetic embedding vectors using a labeled dataset comprising paired samples of course accent phonetic embedding vectors and corresponding target accent phonetic embedding vectors; and comprises an encoder layer configured to encode the phonetic embedding vectors into a latent representation and a decoder layer configured to decode the latent representation to generate the transformed phonetic embedding vectors.
In an analogous system similarly converting speech, Rafii discloses wherein a machine learning model is trained to learn a mapping between the phonetic embedding vectors and the transformed phonetic embedding vectors using a labeled dataset comprising paired samples of course accent phonetic embedding vectors and corresponding target accent phonetic embedding vectors (“Preferably a labeled dataset of corresponding pairs from the first and second speech articulation distributions is created. This labeled data set is used to train a speech articulation transformation model such that when trained, if the model is given an input from the first articulation distribution, it generates in real time an enhanced intelligibility output from the second articulation distribution. In this fashion the listener can hear in real time a more intelligible version of the input speech signal than if such methodology were not used”, col. 4, lines 28-37); and comprises an encoder layer configured to encode the phonetic embedding vectors into a latent representation and a decoder layer configured to decode the latent representation to generate the transformed phonetic embedding vectors (“the speech is encoded to a set of latent states, and then decoded from these latent states directly to the target output speech”, col. 6, lines 48-52).
It would have been obvious to one with ordinary skill in the art before the effective date of the claimed invention to combine the references to yield the predictable result of wherein Keshet’s machine learning model is trained to learn a mapping between the phonetic embedding vectors and the transformed phonetic embedding vectors using a labeled dataset comprising paired samples of course accent phonetic embedding vectors and corresponding target accent phonetic embedding vectors; and comprises an encoder layer configured to encode the phonetic embedding vectors into a latent representation and a decoder layer configured to decode the latent representation to generate the transformed phonetic embedding vectors because training artificial intelligence (AI) models using parallel data, if available, is simple and effective. Further, encoder/decoder networks in AI are standard.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Fan et al. (US 2023/0223006) discloses obtaining a set of phonetic embedding vectors for phonetic content representing a source accent and obtained from input audio data (“The terminal inputs the first voice into a voice feature extraction model, and extracts a PPG feature of the first voice by using the voice feature extraction model”, [0084], see [0120] for accent); and applying a trained machine learning model to the set of phonetic embedding vectors to generate a set of transformed phonetic embedding vectors corresponding to phonetic characteristics of speech data in a target accent (“The terminal inputs the style feature and the PPG feature into a voice fusion model for fusion, to obtain a second voice.”, [0096], see [0120] for accent).
Zhao et al. (US PGPub 2023/0335107) discloses a reference-free foreign accent conversion (FAC) computer system and methods for training models, utilizing a library of algorithms, to directly transform utterances from a foreign, non-native speaker (L2) or second language (L2) speaker to have the accent of a native (L1) speaker. The models in the reference-free FAC computer system are a speech-independent acoustic model to extract speaker independent speech embeddings from an L1 speaker utterance and/or the L2 speaker, a speech synthesizer to generate L1 speaker reference-based golden-speaker utterances and a pronunciation correction model to generate a L2 speaker reference-free golden speaker utterances.
Wang et al. (US PGPub 2021/0193160) discloses obtaining a to-be-converted voice, and extracting acoustic features of the to-be-converted voice; obtaining a source vector corresponding to the to-be-converted voice from a source vector pool, and selecting a target vector corresponding to the target voice from the target vector pool; obtaining acoustic features of the target voice output by the voice conversion model by using the acoustic features of the to-be-converted voice, the source vector corresponding to the to-be-converted voice, and the target vector corresponding to the target voice as an input of the voice conversion model; and obtaining the target voice by converting the acoustic features of the target voice using a vocoder.
Aryal et al. ("Articulatory-based conversion of foreign accents with deep neural networks." Sixteenth Annual Conference of the International Speech Communication Association. 2015) discloses an articulatory-based method for real-time accent conversion using deep neural networks (DNN). The approach consists of two steps. First, a DNN articulatory synthesizer for the non-native speaker that estimates acoustics from contextualized articulatory gestures is trained. Then the DNN is driven with articulatory gestures from a reference native speaker –mapped to the nonnative articulatory space via a Procrustes transform.
Liu et al. ("End-to-end accent conversion without using native utterances." ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2020) discloses an end-to-end framework, which is able to conduct AC (accent conversion) from non-native-accented utterances without using any native-accented utterances during online conversion. This is achieved by independently extracting linguistic and speaker representations from non-native accented speech and condition a speech synthesis model on these representations to generate native-accented speech.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAMUEL G NEWAY whose telephone number is (571)270-1058. The examiner can normally be reached Monday-Friday 9:00am-5:00pm EST.
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, Daniel Washburn can be reached at 571-272-5551. 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.
/SAMUEL G NEWAY/Primary Examiner, Art Unit 2657
Prosecution Insights