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 amendment filed March 2nd, 2026 has been entered. Claims 1, 9, and 12-14 have been amended. Claims 10 and 11 have been cancelled. Claims 1-9 and 12-15 are pending and have been examined. Applicant’s amendments to the claims have overcome the rejections under 35 U.S.C. 112 previously set forth.
Response to Arguments
Applicant’s amendments and arguments, see pages 9-13 of the applicant's response, filed March 2nd, 2026, with respect to the rejection of claims 1-2, 4-8, 13, and 15 under 35 U.S.C. 101 have been fully considered and are persuasive. The rejection of October 1st, 2025 has been withdrawn.
Applicant’s amendments and arguments, see pages 13-16 of the applicant's response, filed March 2nd, 2026, with respect to the rejection of claims 1-8 and 12-15 under 35 U.S.C. 103 have been fully considered and are persuasive. The rejection of October 1st, 2025 has been withdrawn.
Applicant's arguments regarding the rejection of claims 9 and 10 under 35 U.S.C. 103 filed March 2nd, 2026 have been fully considered but they are not persuasive.
The applicant argues that the cited references do not disclose or teach “an intermediate variable” as claimed in amended claim 9 and cancelled claim 10. The examiner respectfully disagrees. As disclosed in fig. 5C and Col. 17, line 52-Col. 18 line 21 of Klimkov, the sampled value, which is a variable since it’s being sampled from a distribution, is concatenated with the encoded linguistic unit data before being further processed. As such, the examiner holds that at least based on the broadest reasonable interpretation of the claim language, the sampled value is an intermediate variable, and thus the cited references fully disclose the language of the claims.
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.
Claim(s) 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Klimkov in view of Zhou et al. (US Pat. Pub. No. 2022/0335925 A1 hereinafter Zhou).
Regarding claim 9, Klimkov discloses a computer implemented method of training a text to speech synthesis model, using a corpus of data comprising a plurality of speech signals spoken in a first voice and a plurality of corresponding text signals, the method comprising: extracting acoustic data from the speech signals; generating one or more acoustic data characteristics corresponding to the first voice from the extracted acoustic data (Klimkov, Col. 8, lines 21-30: "To create the different voice corpuses, a multitude of TTS training utterances may be spoken by an individual and recorded by the system. The audio associated with the TTS training utterances may then be split into small audio segments and stored as part of a voice corpus. The individual speaking the TTS training utterances may speak in different voice qualities to create the customized voice corpuses, for example the individual may whisper the training utterances, say them in an excited voice, and so on."; Col. 7, lines 20-24: "an index entry for a particular unit may include information such as a particular unit's pitch, energy, duration, harmonics, center frequency, where the phonetic unit appears in a word, sentence, or phrase, the neighboring phonetic units, or the like."); generating an output speech signal in an audio file or a video file using a text to speech synthesis model taking a text signal from the corpus as input and using the extracted acoustic data (Klimkov, Col. 8, lines 32-35: "The customized voice corpus 278 may then be used during runtime to perform unit selection to synthesize speech having a speech quality corresponding to the input speech quality."); updating one or more parameters of the text to speech synthesis model based on the corresponding speech signal from the corpus (Klimkov, Col. 8, lines 2-6: "To improve performance, the TTS component 295 may revise/update the contents of the TTS storage 280 based on feedback of the results of TTS processing, thus enabling the TTS component 295 to improve speech recognition."); generating acoustic data using an acoustic feature predictor model taking data extracted from a text signal in the corpus as input (Klimkov, Col. 7, lines 20-24: "an index entry for a particular unit may include information such as a particular unit's pitch, energy, duration, harmonics, center frequency, where the phonetic unit appears in a word, sentence, or phrase, the neighboring phonetic units, or the like."); and updating one or more parameters of the acoustic feature predictor model based on the extracted acoustic data from the corresponding speech signal (Klimkov, Col. 8, lines 2-6: "To improve performance, the TTS component 295 may revise/update the contents of the TTS storage 280 based on feedback of the results of TTS processing, thus enabling the TTS component 295 to improve speech recognition."); wherein generating acoustic data using an acoustic feature predictor model comprises: generating one or more parameters representing a probability distribution for an intermediate variable using an acoustic feature predictor encoder taking the extracted acoustic data and the data extracted from the text signal as input (Klimkov, Col. 17, lines 58-67: " the source encoder with vocal characteristics prediction 540, by contrast, determines a probability distribution of values for each of the values of the encoded source feature vector 532. The probability distribution may represent a likelihood that a given acoustic feature corresponds to a portion of a linguistic unit and/or the audio data representing the linguistic unit. In some embodiments, the probability distribution may be represented by a mean and a standard deviation distribution across the linguistic unit."); sampling an intermediate variable from the probability distribution, wherein the intermediate variable comprises a latent vector (Klimkov, Col. 17 line 67-Col. 18, line 2: "The sample component 542 may, given the determined means and standard deviations, sample a value for each feature for each linguistic unit."); and generating the acoustic data taking the intermediate variable and the data extracted from the text signal as input to an acoustic feature predictor decoder (Klimkov, Col. 17, lines 22-28: "A feature concatenation component 514 may receive the context vector output by the target encoder 504 and the encoded source feature vector and modify the context vector in accordance with the encoded source feature vector to generate a modified context vector; this modified context vector may then be processed by the attention mechanism 506 and decoder 508 to determine the spectrogram data 606."). However, Klimkov fails to expressly recite updating one or more parameters of the text to speech synthesis model based on the corresponding speech signal from the corpus using a gradient descent update method.
Zhou teaches updating one or more parameters of the text to speech synthesis model based on the corresponding speech signal from the corpus using a gradient descent update method (Zhou, [0031]: “The voice synthesizer (135) adapts a machine learning model, like a neural network, to take language input (130) in the form of voice audio or text and produce an output waveform (140) of synthesized speech in a style of the target source (105). Adaption of the model can be performed by updating the model and the embedding vector through stochastic gradient descent.”).
Klimkov and Zhou are analogous arts because they both belong to the same field of speech processing. It would have been obvious to one of ordinary skill in the art before the effective filing date if the claimed invention to have modified the vocal characteristic transfer system of Klimkov to incorporate the teachings of Zhou to use a gradient descent update method. This allows the speech synthesis model to be updated effectively (Zhou, [0031]). Updating the model improves its effectiveness.
Allowable Subject Matter
Claims 1-8 and 13-15 allowed.
Claim 12 objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 1, the examiner agrees with the applicant’s argument that the limitation “obtaining a second speech signal corresponding to the second text spoken in the first language and in a second voice” is not fully disclosed by the prior art references used in the previous rejection. Furthermore, the prior art search did not yield any references that disclosed the limitation, nor any that disclosed the limitation of “generating an initial output speech signal using a text to speech synthesis model taking the second text data as input, the output speech signal corresponding to the second text spoken in the first language in a first voice”, particularly in combination with the other limitations of claim 1. Furthermore, the prior art search did not yield any references that would have been obvious to one of ordinary skill in the art to have combined to yield the claimed invention of claim 1 before the effective filing date of the claimed invention. As such, claim 1 is allowable.
Regarding claims 13 and 14, the claims recite limitations comparable to those of claim 1, and thus are allowable for the same reasons as stated above with regards to claim 1.
Regarding claim 12, the claim recites limitations comparable to those of claim 1, and thus contains allowable subject matter for the same reasons as stated above with regards to claim 1.
Regarding claims 1-8 and 15, each of these claims depends on claim 1 discussed above, or on another dependent claim, and therefore incorporate all limitations therefrom. As such, claims 1-8 and 15 are allowable for at least the same reasons as stated above with regards to claims 1.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Liu et al. (US Pat. Pub. No. 2009/0037179 A1) discloses a method and apparatus for automatically converting voice.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TYLER J BECKER whose telephone number is (703)756-1271. The examiner can normally be reached M-Th, 7:15am-5:45pm PT.
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.
/TYLER BECKER/ Examiner, Art Unit 2657
/DANIEL C WASHBURN/ Supervisory Patent Examiner, Art Unit 2657
Prosecution Insights