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 .
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 10, 11 and 20 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 particular, claims 10 and 20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being incomplete for omitting essential elements, such omission amounting to a gap between the elements. See MPEP § 2172.01. In particular, claim 10 (dependent from claim 1) recites “determining a value of a third loss function of the speech synthesis model based on the difference between the synthesized speech and the standard speech …” while claim 20 (dependent from claim 17) recites “determine a value of a third loss function of the speech synthesis model based on the difference between the synthesized speech and the standard speech …”. The omitted elements are: the “first loss function” and the “second loss function:” before the claimed “third loss function”. Claim 11 is rejected as dependent from claim 10. The language is interpreted as claimed. Appropriate correction is required.
Claim Objections
Claim 13 is objected to because of the following informalities: “wherein in order to performing …” as recited in the claim should be “wherein in order to perform …”. Appropriate correction is required.
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.
1. Claims 1, 3, 5, 6, 8, 12, 14 and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang et al CN 113870827 A (“Zhang”) in view of Kim et al US 2020/10082807 A1 (“Kim”)
Per claim 1, Kim discloses a method for training a speech synthesis model, performed by an electronic device, the method comprising:
obtaining a text sample and a standard speech corresponding to the text sample (obtaining unit 501, for obtaining the training sample, the training sample comprises training the voice information and the training voice information corresponding to the training text information, the training voice information and the training text information indicating the same content …, twelfth page, third para.);
performing speech bit stream prediction on the text sample by using the speech synthesis model, to obtain a speech bit stream corresponding to the text sample (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.);
decoding the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum, twelfth page, seventeenth para.; through the vocoder in the voice synthesis model, converting the voice spectrum to obtain the target voice information, twelfth page, nineteenth para.); and
updating a model parameter of the speech synthesis model based on a difference between the synthesized speech and the standard speech (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para., training model based on loss value as implying updating model parameter),
Zhang does not explicitly disclose the speech synthesis model being configured to output, based on inputted target text, a synthesized speech of the target text
However, this feature is taught by Kim (A loss function may be defined by comparing an output obtained by entering a text as an input to an answer speech signal. The text-to-speech synthesis apparatus may learn the loss function through an error back propagation algorithm and thus finally may obtain a single artificial neural network text-to-speech synthesis model that outputs a desired speech when any text is input, para. [0081])
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to combine the teachings of Kim with the method of Zhang in arriving at the missing features of Zhang, because such combination would have resulted in obtaining a model that provides desired speech to user provided input text (Kim, para. [0081]).
Per claim 3, Zhang in view of Kim discloses the method according to claim 1,
Zhang discloses: wherein the performing speech bit stream prediction on the text sample by using the speech synthesis model, to obtain a speech bit stream corresponding to the text sample comprises: performing speech bit stream prediction on the text sample by using an acoustic model in the speech synthesis model, to obtain the speech bit stream corresponding to the text sample (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.), and
wherein the decoding the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample comprises: decoding the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum, twelfth page, seventeenth para.; through the vocoder in the voice synthesis model, converting the voice spectrum to obtain the target voice information, twelfth page, nineteenth para.).
Per claim 5, Zhang in view of Kim discloses the method according to claim 3,
Zhang discloses wherein before the performing speech bit stream prediction on the text sample by using the speech synthesis model, to obtain a speech bit stream corresponding to the text sample, the method further comprises: encoding the standard speech, to obtain a standard speech bit stream (In one embodiment, the processing unit 502 through the parameter encoder to encode the training voice information processing, obtaining the training voice information of the embedded information …, twelfth page, eighth para.);
performing speech bit stream prediction on the text sample by using an initial acoustic model, to obtain a target speech bit stream (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.); and
updating a model parameter of the initial acoustic model based on a difference between the standard speech bit stream and the target speech bit stream, and determining an updated initial acoustic model as the acoustic model (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para.).
Per claim 6, Zhang in view of Kim discloses the method according to claim 3,
Zhang discloses: wherein before the decoding the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample, the method further comprises: encoding the standard speech, to obtain a standard speech bit stream (In one embodiment, the processing unit 502 through the parameter encoder to encode the training voice information processing, obtaining the training voice information of the embedded information …, twelfth page, eighth para.);
decoding the standard speech bit stream by using an initial speech decoding model, to obtain a decoded speech (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum …, twelfth page); and
updating a model parameter of the initial speech decoding model based on a difference between the standard speech and the decoded speech, and determining an updated initial speech decoding model as the speech decoding model (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para.).
Per claim 8, Zhang in view of Kim discloses the method according to claim 6,
Zhang discloses: wherein the encoding the standard speech, to obtain a standard speech bit stream comprises: encoding the standard speech by using a speech encoding model, to obtain the standard speech bit stream (In one embodiment, the processing unit 502 through the parameter encoder to encode the training voice information processing, obtaining the training voice information of the embedded information …, twelfth page, eighth para.); and
the method further comprises: updating a model parameter of the speech encoding model based on the difference between the standard speech and the decoded speech (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para.).
Per claim 12, Zhang discloses an apparatus for training a speech synthesis model, comprising:
a memory storing a plurality of computer-executable instructions (fourth page, first para.); and
a processor configured to execute the plurality of computer-executable instructions, wherein upon execution of the plurality of computer-executable instructions, the processor is configured to: obtain a text sample and a standard speech corresponding to the text sample (fourth page, first para.; obtaining unit 501, for obtaining the training sample, the training sample comprises training the voice information and the training voice information corresponding to the training text information, the training voice information and the training text information indicating the same content …, twelfth page, third para.);
perform speech bit stream prediction on the text sample by using the speech synthesis model, to obtain a speech bit stream corresponding to the text sample (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.);
decode the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum, twelfth page, seventeenth para.; through the vocoder in the voice synthesis model, converting the voice spectrum to obtain the target voice information, twelfth page, nineteenth para.); and
update a model parameter of the speech synthesis model based on a difference between the synthesized speech and the standard speech (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para., training model based on loss value as implying updating model parameter),
Zhang does not explicitly disclose the speech synthesis model being configured to output, based on inputted target text, a synthesized speech of the target text
However, this feature is taught by Kim (A loss function may be defined by comparing an output obtained by entering a text as an input to an answer speech signal. The text-to-speech synthesis apparatus may learn the loss function through an error back propagation algorithm and thus finally may obtain a single artificial neural network text-to-speech synthesis model that outputs a desired speech when any text is input, para. [0081])
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to combine the teachings of Kim with the apparatus of Zhang in arriving at the missing features of Zhang, because such combination would have resulted in obtaining a model that provides desired speech to user provided input text (Kim, para. [0081]).
Per claim 14, Zhang in view of Kim discloses the apparatus according to claim 12,
Zhang discloses: wherein in order to perform speech bit stream prediction on the text sample by using the speech synthesis model, to obtain the speech bit stream corresponding to the text sample, the processor, upon execution of the plurality of computer-executable instructions, is configured to: perform speech bit stream prediction on the text sample by using an acoustic model in the speech synthesis model, to obtain the speech bit stream corresponding to the text sample (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.), and
wherein in order to decode the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample, the processor, upon execution of the plurality of computer-executable instructions, is configured to: decode the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum, twelfth page, seventeenth para.; through the vocoder in the voice synthesis model, converting the voice spectrum to obtain the target voice information, twelfth page, nineteenth para.).
Per claim 16, Zhang in view of Kim discloses the apparatus according to claim 14,
Zhang discloses: wherein before performance of the speech bit stream prediction on the text sample by using the speech synthesis model, to obtain a speech bit stream corresponding to the text sample, the processor, upon execution of the plurality of computer-executable instructions, is further configured to: encode the standard speech, to obtain a standard speech bit stream (In one embodiment, the processing unit 502 through the parameter encoder to encode the training voice information processing, obtaining the training voice information of the embedded information …, twelfth page, eighth para.);
perform speech bit stream prediction on the text sample by using an initial acoustic model, to obtain a target speech bit stream (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.); and
update a model parameter of the initial acoustic model based on a difference between the standard speech bit stream and the target speech bit stream, and determine an updated initial acoustic model as the acoustic model (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para.).
Per claim 17, Zhang discloses a non-transitory computer-readable storage medium storing a plurality of computer-executable instructions, wherein when executed by a processor, the plurality of computer- executable instructions cause the processor to:
obtain a text sample and a standard speech corresponding to the text sample (obtaining unit 501, for obtaining the training sample, the training sample comprises training the voice information and the training voice information corresponding to the training text information, the training voice information and the training text information indicating the same content …, twelfth page, third para.);
perform speech bit stream prediction on the text sample by using the speech synthesis model, to obtain a speech bit stream corresponding to the text sample (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.);
decode the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum, twelfth page, seventeenth para.; through the vocoder in the voice synthesis model, converting the voice spectrum to obtain the target voice information, twelfth page, nineteenth para.); and
update a model parameter of the speech synthesis model based on a difference between the synthesized speech and the standard speech (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para., training model based on loss value as implying updating model parameter),
Zhang does not explicitly disclose the speech synthesis model being configured to output, based on inputted target text, a synthesized speech of the target text
However, this feature is taught by Kim (A loss function may be defined by comparing an output obtained by entering a text as an input to an answer speech signal. The text-to-speech synthesis apparatus may learn the loss function through an error back propagation algorithm and thus finally may obtain a single artificial neural network text-to-speech synthesis model that outputs a desired speech when any text is input, para. [0081])
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to combine the teachings of Kim with the medium of Zhang in arriving at the missing features of Zhang, because such combination would have resulted in obtaining a model that provides desired speech to user provided input text (Kim, para. [0081]).
Per claim 18, Zhang in view of Kim discloses the non-transitory computer-readable storage medium according to claim 17,
Zhang discloses: wherein in order for the processor to perform speech bit stream prediction on the text sample by using the speech synthesis model, to obtain the speech bit stream corresponding to the text sample, the plurality of computer-executable instructions, when executed by the processor, is configured to cause the processor to: perform speech bit stream prediction on the text sample by using an acoustic model in the speech synthesis model, to obtain the speech bit stream corresponding to the text sample (the processing unit 502 is further used for coding processing the training text information through the voice synthesis model to obtain the phoneme data of the training text information, twelfth page, fifth para.), and
wherein in order for the processor to decode the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample, the plurality of computer-executable instructions, when executed by the processor, is configured to cause the processor to: decode the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum, twelfth page, seventeenth para.; through the vocoder in the voice synthesis model, converting the voice spectrum to obtain the target voice information, twelfth page, nineteenth para.).
Per claim 19, Zhang in view of Kim discloses the non-transitory computer-readable storage medium according to claim 18,
Zhang discloses: wherein before the decoding of the speech bit stream by using the speech synthesis model, to obtain a synthesized speech corresponding to the text sample, the plurality of computer-executable instructions, when executed by the processor, cause the processor to: encode the standard speech, to obtain a standard speech bit stream (In one embodiment, the processing unit 502 through the parameter encoder to encode the training voice information processing, obtaining the training voice information of the embedded information …, twelfth page, eighth para.);
decode the standard speech bit stream by using an initial speech decoding model, to obtain a decoded speech (through the context decoder in the speech synthesis model, decoding the embedded information and the phoneme data to obtain the speech spectrum …, twelfth page); and
update a model parameter of the initial speech decoding model based on a difference between the standard speech and the decoded speech, and determine an updated initial speech decoding model as the speech decoding model (In the specific implementation, the first electronic device can compare the training voice information and the target voice information in the training sample to obtain the loss value of the voice synthesis model, then training the voice synthesis model based on the loss value, obtaining the voice synthesis model after training, eighth page, ninth para.).
2. Claims 2 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Kim as applied to claims 1 and 12 above, and further in view of Lin et al US 2024/0420678 A1 (“Lin”)
Per claim 2, Zhang in view of Kim discloses the method according to claim 1,
Zhang discloses wherein the performing speech bit stream prediction on the text sample, to obtain a speech bit stream corresponding to the text sample comprises: performing word segmentation on the text sample to obtain a plurality of word segments, and performing feature extraction on each word segment to obtain a word segment feature of each word segment (performing word segmentation processing to the training text information through the voice synthesis model to obtain the text string, twelfth page, thirteenth para.);
obtaining a phoneme of each piece of text in the text sample (through the G2P module in the voice synthesis model, converting the text string to obtain the phoneme sequence, fourteenth para.);
Zhang in view of Kim does not explicitly disclose performing pronunciation duration prediction on each phoneme, to obtain pronunciation duration of each phoneme, performing, for each word segment, speech bit stream prediction on the word segment based on pronunciation duration of a phoneme of text comprised in the word segment and the word segment feature of the word segment, to obtain a word segment bit stream of the word segment or splicing word segment bit streams of the plurality of word segments, to obtain the speech bit stream corresponding to the text sample
However, these features are taught by Lin:
performing pronunciation duration prediction on each phoneme, to obtain pronunciation duration of each phoneme (para. [0072]; para. [0078]);
performing, for each word segment, speech bit stream prediction on the word segment based on pronunciation duration of a phoneme of text comprised in the word segment and the word segment feature of the word segment, to obtain a word segment bit stream of the word segment (para. [0072]); and
splicing word segment bit streams of the plurality of word segments, to obtain the speech bit stream corresponding to the text sample (para. [0094]-[0099])
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to combine the teachings of Lin with the method of Zhang in view of Kim in arriving at the missing features of Zhang in view of Kim, because such combination would have resulted in enabling synthesized audio to be more natural, cadenced, and aligned with the intended semantics of a speaker (Lin, Abstract).
Per claim 13, Zhang in view of Kim discloses the apparatus according to claim 12,
Zhang discloses: wherein in order to performing speech bit stream prediction on the text sample, to obtain the speech bit stream corresponding to the text sample, the processor, upon execution of the plurality of computer-executable instructions, is configured to: perform word segmentation on the text sample to obtain a plurality of word segments, and perform feature extraction on each word segment to obtain a word segment feature of each word segment (performing word segmentation processing to the training text information through the voice synthesis model to obtain the text string, twelfth page, thirteenth para.);
obtain a phoneme of each piece of text in the text sample (through the G2P module in the voice synthesis model, converting the text string to obtain the phoneme sequence, fourteenth para.), and
Zhang in view of Kim does not explicitly disclose perform pronunciation duration prediction on each phoneme, to obtain pronunciation duration of each phoneme; perform, for each word segment, speech bit stream prediction on the word segment based on pronunciation duration of a phoneme of text comprised in the word segment and the word segment feature of the word segment, to obtain a word segment bit stream of the word segment or splice word segment bit streams of the plurality of word segments, to obtain the speech bit stream corresponding to the text sample.
However, these features are taught by Lin:
perform pronunciation duration prediction on each phoneme, to obtain pronunciation duration of each phoneme (para. [0072]; para. [0078]);
perform, for each word segment, speech bit stream prediction on the word segment based on pronunciation duration of a phoneme of text comprised in the word segment and the word segment feature of the word segment, to obtain a word segment bit stream of the word segment (para. [0072]); and
splice word segment bit streams of the plurality of word segments, to obtain the speech bit stream corresponding to the text sample (para. [0094]-[0099])
It would have been obvious to one of ordinary skill in the art before the effective filing of the instant invention to combine the teachings of Lin with the apparatus of Zhang in view of Kim in arriving at the missing features of Zhang in view of Kim, because such combination would have resulted in enabling synthesized audio to be more natural, cadenced, and aligned with the intended semantics of a speaker (Lin, Abstract).
3. Claims 4 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Kim as applied to claims 3 and 14 above, and further in view of Huang et al US 2022/0189454 A1 (“Huang”) and Da Costa et al “Neural Vocoding for CycleGAN-Based Voice Conversion” (“Da costa”)
Per claim 4, Zhang in view of Kim discloses the method according to claim 3,
Zhang in view of Kim does not explicitly disclose wherein the speech decoding model comprises a plurality of cascaded upsampling layers, and the decoding the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample comprises: performing upsampling on the speech bit stream by using the plurality of cascaded upsampling layers, to obtain the synthesized speech corresponding to the text sample
However, this feature is suggested by Huang that discloses wherein the speech decoding model comprises an upsampling layer, and the decoding the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample comprises: performing upsampling on the speech bit stream by using the upsampling layer, to obtain the synthesized speech corresponding to the text sample (Abstract; para. [0023]-[0024]; para. [0033])
Zhang in view of Kim and Huang does not explicitly disclose the use of cascaded upsampling layers
However, this feature is taught by Da Costa (The generator network cascades downsampling layers, residual blocks [25] and upsampling layers. Each convolutional layer is followed by an Instance Normalization layer and a ReLU non-linear activation …, sec. III)
It would have been obvious to one of ordinary skill in the art before the effective filing of the invention to combine the teachings of Huang with the method of Zhang in view of Kim in arriving at the missing features of Zhang in view of Kim, as well as to combine the teachings of Da Costa with the method of Zhang in view of Kim and Huang in arriving at the missing features of Zhang in view of Kim and Huang, because such combination would have resulted in improving the quality of the final synthesized speech (Huang, para. [0056]) and increasing the resolution of the speech (Da Costa, sec. III)
Per claim 15, Zhang in view of Kim discloses the apparatus according to claim 14,
Zhang in view of Kim does not explicitly disclose wherein the speech decoding model comprises a plurality of cascaded upsampling layers, and in order to decode the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample, the processor, upon execution of the plurality of computer- executable instructions, is configured to: perform upsampling on the speech bit stream by using the plurality of cascaded upsampling layers, to obtain the synthesized speech corresponding to the text sample
However, this feature is suggested by Huang that discloses wherein the speech decoding model comprises a upsampling layer, and in order to decode the speech bit stream by using a speech decoding model in the speech synthesis model, to obtain the synthesized speech corresponding to the text sample, the processor, upon execution of the plurality of computer- executable instructions, is configured to: perform upsampling on the speech bit stream by using the upsampling layer, to obtain the synthesized speech corresponding to the text sample (Abstract; para. [0023]-[0024]; para. [0033])
Zhang in view of Kim and Huang does not explicitly disclose the use of cascaded upsampling layers
However, this feature is taught by Da Costa (The generator network cascades downsampling layers, residual blocks [25] and upsampling layers. Each convolutional layer is followed by an Instance Normalization layer and a ReLU non-linear activation …, sec. III)
It would have been obvious to one of ordinary skill in the art before the effective filing of the invention to combine the teachings of Huang with the apparatus of Zhang in view of Kim in arriving at the missing features of Zhang in view of Kim, as well as to combine the teachings of Da Costa with the apparatus of Zhang in view of Kim and Huang in arriving at the missing features of Zhang in view of Kim and Huang, because such combination would have resulted in improving the quality of the final synthesized speech (Huang, para. [0056]) and increasing the resolution of the speech (Da Costa, sec. III).
4. Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Zhang in view of Kim as applied to claim 5 above, and further in view of Ho et al “Non-parallel Voice Conversion based on Hierarchical Latent Embedding” (“Ho”) and Da Costa et al “Neural Vocoding for CycleGAN-Based Voice Conversion” (“Da costa”)
Per claim 9, Zhang in view of Kim discloses the method according to claim 5,
Zhang in view of Kim does not explicitly disclose wherein the standard speech comprises a plurality of sampling points, and the encoding the standard speech, to obtain a standard speech bit stream comprises: performing downsampling on each sampling point by using a plurality of cascaded downsampling layers, to obtain a standard speech variable of each sampling point or quantizing the standard speech variable of each sampling point, to obtain the standard speech bit stream
However, these features are suggested by Ho:
wherein the standard speech comprises a plurality of sampling points, and the encoding the standard speech, to obtain a standard speech bit stream comprises: performing downsampling on each sampling point by using a downsampling layer, to obtain a standard speech variable of each sampling point (fig. 1); and
quantizing the standard speech variable of each sampling point, to obtain the standard speech bit stream (fig. 1)
Zhang in view of Kim and Ho does not explicitly disclose using a plurality of cascaded downsampling layers,
However, this feature is taught by Da Costa (The generator network cascades downsampling layers, residual blocks [25] and upsampling layers. Each convolutional layer is followed by an Instance Normalization layer and a ReLU non-linear activation …, sec. III)
It would have been obvious to one of ordinary skill in the art before the effective filing of the invention to combine the teachings of Ho with the method of Zhang in view of Kim in arriving at the missing features of Zhang in view of Kim, as well as to combine the teachings of Da Costa with the method of Zhang in view of Kim and Ho in arriving at the missing features of Zhang in view of Kim and Ho, because such combination would have resulted in improving the quality of converted/output speech (Ho, sec. 5), and reducing the resolution of the speech (Da Costa, sec. III).
Allowable Subject Matter
Claims 7 is 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.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO 892 form.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to OLUJIMI A ADESANYA whose telephone number is (571)270-3307. The examiner can normally be reached Monday-Friday 8:30-5:00pm.
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, Richemond Dorvil can be reached at 571-272-7602. 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.
/OLUJIMI A ADESANYA/Primary Examiner, Art Unit 2658
Prosecution Insights