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 .
This action is in response to the Preliminary Amendment filed on January 13, 2025.
Claims 1-10 and 12-21are pending in this action. Claims 1-10 and 12-13 have been amended. Claim 11 has been canceled. Claims 14-21 have been newly added.
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)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1-6, 9-10, 12-13, 17, and 19-21 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Chen et al. (CN 112116904A).
As per claim 1, Chen discloses, a voice processing method, comprising:
performing voice conversion processing based on a user voice of a target user and specified timbre information to obtain a specified converted voice having a specified timbre, wherein the specified timbre information is determined from a plurality of pieces of preset timbre information, and the specified converted voice is a user voice having the specified timbre (“wherein the target user characteristic is extracted from the reference voice characteristic; it can describe the timbre of the reference voice and original language. Therefore, according to the target user characteristic to the target text for voice conversion, considering the timbre and original language of the reference voice, so that the voice conversion sub-model can according to the timbre and the relation between the timbre of the voice to be converted, and the relation between the original language and the target language; The target text is converted into a speech containing a reference speech and a speech belonging to a target language”);
training a voice conversion model based on the user voice of the target user and the specified converted voice to obtain a target voice conversion model (Fig. 5, “obtaining the sample information; the sample information comprises sample text; a first sample voice and a second sample voice; the sample text and the first sample voice belong to the original language; the first sample voice is the same as the semantic of the sample text; the second sample voice is the same as the semantic meaning of the sample text and belongs to the target language; the timbre of the first sample speech and the second sample speech is different, according to the sample information, training the voice conversion model.”);
inputting a target text for voice synthesis and the specified timbre information into a voice synthesis model to generate an intermediate voice having the specified timbre; and
performing voice conversion processing on the intermediate voice by the target voice conversion model to generate a target synthesized voice that matches a timbre of the target user (the voice conversion model is used for according to the reference voice with any timbre and belonging to the original language; the text belonging to the original language is converted into the voice with any timbre and belonging to the target language; the original language is different from the target language”).
As per claim 2, Chen discloses, obtaining a language content feature and a prosodic feature from the user voice of the target user, wherein the performing of the voice conversion processing based on the user voice of the target user and the specified timbre information comprises: performing the voice conversion processing based on the language content feature, the prosodic feature and the specified timbre information (“therefore, the voice conversion model to the sample text feature for acoustic feature extraction process considers the language feature in the sample user feature; so as to improve the accuracy of the extracted acoustic feature, namely improving the alignment effect of the sample text belonging to the original language and the voice belonging to the target language, so as to improve the accuracy of the converted voice in the semantic. and performing voice conversion on the acoustic feature according to the sample user feature, considering the timbre feature in the sample user feature, so that the converted first prediction speech can approach the timbre of the first sample speech, improving the accuracy of the converted speech on the timbre”).
As per claim 3, Chen discloses, the voice synthesis model is obtained by training a preset voice synthesis model using a training sample voice set, the training sample voice set comprising a plurality of sample voices and respective texts and sample timbre information of the sample voices (“obtaining the sample information; the sample information comprises sample text; the first sample speech and the second sample speech; the sample text and the first sample speech belong to the original language; the first sample speech is the same as the semantic of the sample text; the second sample speech is the same as the semantic meaning of the sample text and belongs to the target language; the timbre of the first sample speech and the second sample speech is different; according to the sample information, training the voice conversion mode”).
As per claim 4, Chen discloses, wherein the training of the voice conversion model to obtain the target voice conversion model comprises: training a parallel voice conversion model based on the user voice of the target user and the specified converted voice, and taking the trained parallel voice conversion model as the target voice conversion model (“obtaining the sample information; the sample information comprises sample text; the first sample speech and the second sample speech; the sample text and the first sample speech belong to the original language; the first sample speech is the same as the semantic of the sample text; the second sample speech is the same as the semantic meaning of the sample text and belongs to the target language; the timbre of the first sample speech and the second sample speech is different; according to the sample information, training the voice conversion mode”).
As per claim 5, Chen discloses, further comprising: obtaining a training voice pair and preset timbre information corresponding to the training voice pair, wherein the training voice pair comprises an original voice and an output voice, both comprising a same voice, of a training sample voice set (“In another possible implementation, the voice conversion sub-model comprises a text feature extraction network, acoustic feature extraction network and a voice conversion network, invoking the voice conversion sub-model, according to the target user feature to the target text for voice conversion, obtaining the target voice”); and
training a non-parallel voice conversion model based on the original voice, the output voice, and the preset timbre information corresponding to the training voice pair, and taking the trained non- parallel voice conversion model as a target non-parallel voice conversion model (“according to the timbre difference between the first prediction speech and the first sample speech and the content difference between the first prediction speech and the second sample speech, training speech conversion model”).
As per claim 6, Chen discloses, wherein the training of the non-parallel voice conversion model comprises: performing language content extraction processing on the original voice by a language feature processor of the non-parallel voice conversion model to obtain a language content feature of the original voice; performing prosody extraction processing on the original voice by a prosodic feature processor of the non-parallel voice conversion model to obtain a prosodic feature of the original voice; and training the non-parallel voice conversion model based on the language content feature of the original voice, the prosodic feature of the original voice, the output voice, and the preset timbre information, corresponding to the training voice pair (Fig. 7, description of Fig. 7).
As per claim 9, Chen discloses, wherein the obtaining of the language content feature and the prosodic feature from the user voice of the target user comprises: performing language content extraction processing on the user voice of the target user by a language feature processor of the target non-parallel voice conversion model to obtain the language content feature of the user voice of the target user; and performing prosody extraction processing on the user voice of the target user by a prosodic feature processor of the target non-parallel voice conversion model to obtain the prosodic feature of the user voice of the target user (“therefore, the voice conversion model to the sample text feature for acoustic feature extraction process considers the language feature in the sample user feature; so as to improve the accuracy of the extracted acoustic feature, namely improving the alignment effect of the sample text belonging to the original language and the voice belonging to the target language, so as to improve the accuracy of the converted voice in the semantic. and performing voice conversion on the acoustic feature according to the sample user feature, considering the timbre feature in the sample user feature, so that the converted first prediction speech can approach the timbre of the first sample speech, improving the accuracy of the converted speech on the timbre”).
As per claim 10, Chen discloses, wherein the performing of the voice conversion processing based on the language content feature, the prosodic feature and the specified timbre information comprises: inputting the language content feature of the user voice of the target user, the prosodic feature of the user voice of the target user, and the specified timbre information into the target non-parallel voice conversion model to generate the specified converted voice having the specified timbre (Fig. 4 description).
As per claims 12-13 and 19-21, they are analyzed and thus rejected for the same reasons set forth in the rejection of claims 1-6 and 9-10, because the corresponding claims have similar limitations.
As per claim 17, Chen discloses, wherein the performing of the prosody extraction processing on the original voice by the prosodic feature processor comprises: performing the prosody extraction processing on the original voice by the prosodic feature processor based on at least one of frequency, energy, and a feature relating to voice emotion classification (“the timbre of the first sample voice. Optionally, the voice feature is Mel-scale Frequency Cepstral Com (MFCC)”).
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) 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (CN 112116904A) as applied to claim 1 above, and further in view of Yin (CN111292720A).
As per claim 14, Chen does not explicitly disclose, but Yin discloses, wherein the preset voice synthesis model comprises at least one of tacotron and fastspeech (“In this disclosure, various languages language feature vector can be in voice characteristic information and multilingual text input to the existing voice synthesis model (e.g., Tacotron model Deepvoice 3 model, Tacotron2 model, Wavenet model, etc.), obtaining the Mel spectrum characteristic information corresponding with the multilingual text”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Chen by including voice synthesis model comprises tacotron as taught by Yin because obtaining the language feature vector of voice characteristic information of each language multilingual text and the language text, wherein the voice feature information comprises a phoneme, tone, participle and prosodic boundary, the language feature vector comprises in corresponding text belonging to the language mark of each phoneme of the current language (Summary of the invention).
Claim(s) 15 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (CN 112116904A) as applied to claim 6 above, and further in view of Pollet et al. (CN110050302A).
As per claim 15, Chen does not explicitly disclose, but Pollet discloses, inputting the original voice into the language feature processor, and determining an output of a specific hidden layer output of the voice recognition model as the language content feature of the original voice (Fig. 2 description, “LSTM-RNN 203 via an input layer, one or more hidden layer and an output layer processing language feature 201. LSTM-RNN 203 outputs speech data 205 via the output layer”).
As per claim 18, Chen does not disclose, but Pollet discloses, wherein the non-parallel voice conversion model comprises at least one of a convolutional neural network, a recurrent neural network, a Transformer (Fig,2).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Chen by including determining an output of a specific hidden layer output of the voice recognition model as the language content feature of the original voice as taught by Pollet because generating natural sounding synthesizing speech.
Claim(s) 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (CN 112116904A) as applied to claim 6 above, and further in view of Well-known prior art.
As per claim 16, Chen does not explicitly discloses, wherein the performing of the language content extraction processing on the original voice by the language feature processor of the non-parallel voice conversion model to obtain the language content feature of the original voice comprises:compressing and quantifying the original voice into a plurality of voice units by using a Vector Quantised-Variational AutoEncoder model; performing a self-restoration training process on the voice units to obtain a plurality of restored voice units independent of timbre; and determining the restored voice units as the language content feature of the original voice. Official Notice is taken on the well-known a Vector Quantised-Variational AutoEncoder model.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to modify the invention of Chen by including a Vector Quantised-Variational AutoEncoder model as well-known in the art because all the claimed elements were known in the art and one skilled in the art could have combined the elements as claimed by known methods with no change in their respective functions, and the combination would have yielded predictable results to one ordinary skill in the art at the time of the invention.
“common sense teaches, however, that familiar items may have obvious uses beyond their primary purposes, and in many cases a person of ordinary skill will be able to fit the teachings of multiple patents together like pieces of a puzzle.” KSR Int' l Co. V. Teleflex Inc. 550 U.S.-,82USPQ2d 1385 (Supreme Court 2007) (KSR).
Allowable Subject Matter
Claims 7 and 8 are 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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Abul K. Azad whose telephone number is (571) 272-7599. If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Bhavesh Mehta, can be reached at (571) 272-7453.
Any response to this action should be mailed to:
Commissioner for Patents
P.O. Box 1450
Alexandria, VA 22313-1450
Or faxed to: (571) 273-8300.
Hand-delivered responses should be brought to 401 Dulany Street, Alexandria, VA-22314 (Customer Service Window).
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
June 24, 2026
/ABUL K AZAD/Primary Examiner, Art Unit 2656
Prosecution Insights