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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on June 24, 2026 has been entered.
Response to Arguments
Applicants argue that the prior art cited fails to teach the claims as amended. Applicants’ arguments are persuasive, but are moot in view of new ground of rejection.
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(s) 1-19 is/are rejected under 35 U.S.C. 103(a) as being anticipated by Kapilow et al. (USPN 7,454,348) in view of Kollada et al. (PGPUB 2022/0392637), hereinafter referenced as Kollada.
Regarding claims 1 and 10, Kapilow discloses a processor-implemented method and system, hereinafter referenced a method of constructing a training dataset for a text-to-speech model, comprising:
collecting, by a processor, speech data including different speech utterance information (fig. 2a, elements 302-304 with column 2, lines 58-67) comprising digitized audio signals and corresponding metadata including at least on of language, speaker and emotion (column 4, line 58 – column 5, line 20);
wherein the text-to-speech model uses the synthetic utterance dataset such that synthesis performance across variations of language, speaker, and emotion is improved (column 4, line 58 – column 5, line 20), but does not specifically teach increasing, by the processor, the speech data by fusing the collected speech data having different speech utterance information within a single utterance time sequence, including combining according to time-series portions of at least two speech data samples to generate increased speech data such that speech utterance information of the increased speech data changes over time within the single utterance and generating, by the processor, a training dataset by storing the increased speech data fused feature sequence as a synthetic utterance dataset configured as a training input.
Kollada discloses a method comprising:
increasing, by the processor, the speech data by fusing the collected speech data having different speech utterance information within a single utterance time sequence (different features using a frame-based speech encoder), including combining according to time-series portions of at least two speech data samples to generate increased speech data such that speech utterance information of the increased speech data changes over time within the single utterance (preserve timing; p. 0053, 0062-0064, 0114, 0104); and
generating, by the processor, a training dataset by storing the increased speech data fused feature sequence as a synthetic utterance dataset configured as a training input (training; p. 0082, 0116, 0053-0057), to provide quality data.
Therefore, it would have been obvious to one of ordinary skill of the art, before the effective filing data of the claimed invention, to modify the method as described above, for capturing and preserving interactions as well as timing information for fused data.
Regarding claim 2, Kapilow discloses a method wherein the training dataset includes a text on speech data and speech utterance information as input data of the speech synthesis model, wherein the training dataset includes speech data as output data of the speech synthesis model (synthetic; column 2, lines 36-67).
Regarding claim 3, Kapilow discloses a method wherein the speech utterance information includes at least one of a language of a text, a speaker uttering the text, and an emotion of the speaker uttering the text (emotion; column 2, lines 25-35).
Regarding claim 4, Kapilow discloses a method wherein the increasing comprises fusing speech data of different languages within one utterance according to time series (languages/accents; column 2, lines 25-35).
` Regarding claim 5, Kapilow discloses a method wherein the increasing comprises fusing speech data of different speakers within one utterance according to time series (blended characteristics of two voices; column 3, lines 2-27).
Regarding claim 6, it is interpreted and rejected for similar reasons as set forth in the combination of claims 4-5.
Regarding claim 7, Kapilow discloses a method wherein the step of increasing comprises fusing speech data of different emotions within one utterance according to time series (emotion; column 2, lines 25-35).
Regarding claim 8, Kapilow discloses a method wherein the increasing comprises fusing speech data of different paralinguistic expressions within one utterance according to time series (voice characteristics; column 2, lines 10-67).
Regarding claim 9, Kapilow discloses a method further comprising training the speech synthesis model with a generated training dataset (train; column 4, lines 10-21).
Regarding claim 11, Kapilow discloses a training method of a speech synthesis model, the method comprising:
a step of increasing speech data by fusing speech data having different speech utterance information within one utterance (blend voice; fig. 3, element 308 with column 3, lines 2-27);
a step of generating a training dataset by using the increased speech data (train; column 4, lines 10-21); and
a step of training the speech synthesis model with the generated training dataset (synthetic; column 2, lines 36-67).
Regarding claim 12, Kapilow discloses a training method wherein the training dataset includes a text on speech data and speech utterance information as input data of the speech synthesis model, wherein the training dataset includes speech data as output data of the speech synthesis model (column 4, line 58 – column 5, line 20).
Regarding claim 13, Kapilow discloses a training method wherein the speech utterance information includes at least one of a language of a text, a speaker uttering the text, and an emotion of the speaker uttering the text (language/emotion; column 5, lines 1-20).
Regarding claim 14, it is interpreted and rejected for similar reasons as set forth above. In addition, Kapilow discloses a training method wherein, for the increasing, the processor is configured to fuse speech data of different languages (column 4, lines 10-40).
Regarding claim 15, it is interpreted and rejected for similar reasons as set forth above. In addition, Kapilow discloses a training method wherein, for the increasing, the processor is configured to fuse speech data of different speakers (column 4, lines 10-40).
Regarding claim 16, it is interpreted and rejected for similar reasons as set forth above. In addition, Kapilow discloses a training method wherein, for the increasing, the processor is configured to fuse speech data of different languages (column 5, lines 1-20) and different speakers (column 4, lines 10-40).
Regarding claim 17, it is interpreted and rejected for similar reasons as set forth above. In addition, Kapilow discloses a training method wherein, for the increasing, the processor is configured to fuse speech data of different emotions (column 5, lines 1-20).
Regarding claim 18, it is interpreted and rejected for similar reasons as set forth above. In addition, Kapilow discloses a training method wherein, for the increasing, the processor is configured to fuse speech data of different paralinguistic expressions (pitch; column 3, line 28 – column 4, line 9).
Regarding claim 19, it is interpreted and rejected for similar reasons as set forth above. In addition, Kapilow discloses a training method wherein the processor is further configured to train a speech synthesis model with the generated training dataset (synthesis; column 2, lines 10-67).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JAKIEDA R JACKSON whose telephone number is (571)272-7619. The examiner can normally be reached Mon - Fri 6:30a-2:30p.
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.
/JAKIEDA R JACKSON/Primary Examiner, Art Unit 2657
Prosecution Insights