DETAILED ACTION
Notice of 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 Arguments
Applicant’s amendments and arguments filed 04/13/2026, with respect to claim(s) 1-14 have been fully considered. Applicant amended claims 1, 4, 7, 8, 9, 12 and cancelled claims 2, 3, 10, 11.
35 U.S.C 101 rejections of Claims 1-14 have been withdrawn in view of the amended claims filed on 04/13/2026.
Applicant’s arguments filed 04/13/2026, with respect to claim(s) 1-14, under 35 U.S.C. 103 have been fully considered but they are not persuasive. Applicant argued that the amended claim 1 recites “ inputting the object image into an object classification model…. sound classification model from the first sound sample”, is not supported by cited references, whether taken alone or in combination. Applicant further argued that Xu does not disclose or suggest using a sound classification model to extract sound category characteristics from a first sound sample and then align the output of the object classification model with those characteristics. In other words, Xu is completely silent on the dual-model, cross-modal alignment. Examiner respectfully disagrees. The sound classification model , taught by Xu, is trained by obtaining the sample image, sample text and label data, the sample image comprises a sample object as a virtual character image, the label data comprises sample voice of the sample object corresponding to the sample text. So, Xu is teaching a single model but which is performing the same function as a dual model by categorizing target object and labeling the target object with the corresponding voice data and text. Xu in page 3, 6 describes that there can be different category of target object ( virtual character image) such as human with short hair, adult female or can be a cartoon image. Sound feature extraction model is trained with the target object and corresponding sound and text. Examiner believes the previously cited prior art of Xu in view of Chen, still teach the amended claims. Thus, the 35 U.S.C. 103 rejections by the previously cited prior art of record is maintained. Please see the rejections below.
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 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 of this title, 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.
Claims 1, 4-6, 9 and 12-14 are rejected under 35 U.S.C. 103 as being unpatentable over Xu et al. ( CN 114596836 A), hereinafter referenced as Xu, in view of Chen et al. (US 20240107127 A1), hereinafter referenced as Chen.
Regarding Claim 1, Xu teaches a speech generation method comprising:
obtaining an object image of a virtual object ( Xu: Page 6, para.[2], obtaining the target image and target text for speech synthesis, the target image comprises a target object as a virtual character);
inputting the object image into an object classification model to obtain target object category characteristics of the virtual object identified by the object classification model, the object classification model being trained using at least one sample group including a first image sample and a first sound sample belonging to a same object, with training objectives including that object category characteristics identified by the object classification model from the first image sample are consistent with sound category characteristics identified by a sound classification model from the first sound sample ( Xu: Page 3, para.[1], page 6, para.[7], during the training of the TTS model, the obtaining unit is configured to obtain the sample image, sample text and label data, the sample image comprises a sample object as a virtual character image, the label data comprises sample voice of the sample object corresponding to the sample text. The virtual character image in the target image can be the image of human, such as short hair, adult female or the virtual character image in the target image also can be a cartoon image ( object category). Page 7, para.[8], [10], the training of the sound feature extraction model, which can be, for example, deep learning network Deep Neural Network (DNN) model and by obtaining the sample image and the sample image of the annotation data, the sample image comprises a sample object as a virtual character image, the annotation data comprises sample sound characteristic of the sample object);
determining target sound category characteristics corresponding to the virtual object based on the object image( Xu: Page 6, para.[3], inputting the target image to the trained sound feature extraction model to obtain the sound feature of the target object (virtual character));
the determining the target sound category characteristics corresponding to the virtual object comprising determining the target object category characteristics of the virtual object as the target sound category characteristics corresponding to the virtual object ( Xu: Page 3, para.[1], page 6, para.[7], during the training of the TTS model, the obtaining unit is configured to obtain the sample image, sample text and label data, the sample image comprises a sample object as a virtual character image, the label data comprises sample voice of the sample object corresponding to the sample text. The virtual character image in the target image can be the image of human, such as short hair, adult female or the virtual character image in the target image also can be a cartoon image ( object category))
( Xu: page 6, para.[10], sound feature of the target object and the target text of the to-be-synthesized speech input training speech synthesis model, to obtain the target speech of the sound characteristic of the target object output by the speech synthesis model );
Xu while teaching the method of claim 1, fails to explicitly teach the claimed, obtaining text information, the text information being used to describe speech content that needs to be output by the virtual object; and outputting the speech data in a virtual scene in which the virtual object is presented.
However, Chen does teach the claimed, obtaining text information, the text information being used to describe speech content that needs to be output by the virtual object ( Chen: Para.[0251], obtaining subtitle text for the virtual character object which will broadcast the subtitle text ( such as news broadcast));
and outputting the speech data in a virtual scene in which the virtual object is presented ( Chen: Para. [0245], [0270], [0271], Fig. 15 illustrates a virtual scene of broadcasting news by the Avatar ( virtual character object), where the electronic device generates the speech/audio by using the text to speech conversion model from the subtitle).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Chen’s teaching of video display and processing method, apparatus and system, in the field of multimedia technology, into the system and method of voice synthesis, taught by Xu, because, this would improve the quality of the video produced and reduce the time cost of producing the video.(Chen, Para.[0033]).
Claim 9 is non-transitory computer readable storage medium claim containing computer-executable instructions for, when executed by one or more processors ( Xu: Page 3, para.[4], provided a computer readable storage medium which is stored with a computer program, when the computer program is executed by a processor, the processor executes the method), performing the steps in method claim 1 above and as such, claim 9 is similar in scope and content to claim 1 and therefore, claim 9 is rejected under similar rationale as presented against claim 1 above.
Regarding Claim 4, Xu in view of Chen teach the method of claim [[3]] 1 . Xu further teaches, wherein: the sample group is labeled with an actual object identifier ( Xu: Page 2, para.[4], obtaining annotated sample image) ,
and the training objectives also includes that predicted object information of the first image sample determined by using the object classification model is consistent with the actual object identifier labeled by the sample group to which the first image sample belongs ( Xu: Page 8, para.[8], training process includes a sample object prediction value and the real value and calculating the loss value).
Claim 12 is non-transitory computer readable storage medium claim performing the steps in method claim 4 above and as such, claim 12 is similar in scope and content to claim 4 and therefore, claim 12 is rejected under similar rationale as presented against claim 4 above.
Regarding Claim 5, Xu in view of Chen teach the method of claim 4. Xu further teaches, wherein training the object classification model includes: obtaining at least one sample groups ( Xu: Page 10, para.[2], obtaining sample image);
for each sample group, inputting the first image sample in the sample group into an image classification model and the first sound sample in the sample group into the sound classification model, and extracting the sound category characteristics identified by the sound classification model and the object category characteristics identified by the image classification model to obtain the predicted object information corresponding to the first image sample determined by the image classification model ( Xu: Page 10, para.[2], sample image is input into the sound feature extraction model which will output the first prediction sound feature of the sample object in the sample image) ;
and in response to the training objectives not being met based on characteristic similarity, the predicted object information and the actual object identifier corresponding to each sample group, adjusting parameters of the image classification model, and returning to extraction of the sound category characteristics identified by the sound classification model and the object category characteristics identified by the image classification model until the training objectives are met, the image classification model being used to determine a trained object classification model ( Xu: Page 8, para.[7], Page 9, para.[10], para.[5],[10], the loss value is calculated based on the prediction voice spectrum characteristic (predicted value) and sample voice spectrum characteristic (real value). Subsequently, based on the loss value, adjusting the parameter sound feature extraction model ).
Claim 13 is non-transitory computer readable storage medium claim performing the steps in method claim 5 above and as such, claim 13 is similar in scope and content to claim 5 and therefore, claim 13 is rejected under similar rationale as presented against claim 5 above.
Regarding Claim 6, Xu in view of Chen teach the method of claim 1. Xu further teaches, wherein generating the speech data that conforms to the target sound category characteristics based on the text information and the target sound category characteristics includes: using a speech synthesis model to construct the speech data to obtain the speech data with the target sound category characteristics based on the text information and the target sound category characteristics ( Xu: Page 3, para.[1], page 6, para.[10], the speech synthesis model generates the speech corresponding to the sound feature of the target object and the target text).
Claim 14 is non-transitory computer readable storage medium claim performing the steps in method claim 6 above and as such, claim 14 is similar in scope and content to claim 6 and therefore, claim 14 is rejected under similar rationale as presented against claim 6 above.
Claims 7, 8 are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al. (US 20240107127 A1), hereinafter referenced as Chen , in view of Xu et al. ( CN 114596836 A), hereinafter referenced as Xu.
Regarding Claim 7, Chen teaches a virtual object generation method comprising: obtaining an object image used to construct the virtual object ( Chen: Para.[0255], user image is inputted into a preset biometric feature extraction model to extract the user biometric features to obtain an avatar with the user biometric features );
and outputting, in a virtual scene, speech data generated based on text information and the target sound category characteristics ( Chen: Para. [0245], [0270], [0271], Fig. 15 illustrates a virtual scene of broadcasting news by the Avatar ( virtual character object), where the electronic device generates the speech/audio by using the text to speech conversion model from the subtitle).
Chen while teaching the method of claim 7, fails to explicitly teach the claimed, inputting the object image into an object classification model to obtain target object category characteristics of the virtual object identified by the object classification model, the object classification model being trained using at least one sample group including a first image sample and a first sound sample belonging to a same object, with training objectives including that object category characteristics identified by the object classification model from the first image sample are consistent with sound category characteristics identified by a sound classification model from the first sound sample; determining target sound category characteristics corresponding to the virtual object based on the object image; the determining the target sound category characteristics corresponding to the virtual object comprising determining the target object category characteristics of the virtual object as the target sound category characteristics corresponding to the virtual object;
However, Xu does teach the claimed, inputting the object image into an object classification model to obtain target object category characteristics of the virtual object identified by the object classification model, the object classification model being trained using at least one sample group including a first image sample and a first sound sample belonging to a same object, with training objectives including that object category characteristics identified by the object classification model from the first image sample are consistent with sound category characteristics identified by a sound classification model from the first sound sample ( Xu: Page 3, para.[1], page 6, para.[7], during the training of the TTS model, the obtaining unit is configured to obtain the sample image, sample text and label data, the sample image comprises a sample object as a virtual character image, the label data comprises sample voice of the sample object corresponding to the sample text. The virtual character image in the target image can be the image of human, such as short hair, adult female or the virtual character image in the target image also can be a cartoon image ( object category). Page 7, para.[8], [10], the training of the sound feature extraction model, which can be, for example, deep learning network Deep Neural Network (DNN) model and by obtaining the sample image and the sample image of the annotation data, the sample image comprises a sample object as a virtual character image, the annotation data comprises sample sound characteristic of the sample object);
determining target sound category characteristics corresponding to the virtual object based on the object image( Xu: Page 6, para.[3], inputting the target image to the trained sound feature extraction model to obtain the sound feature of the target object (virtual character));
the determining the target sound category characteristics corresponding to the virtual object comprising determining the target object category characteristics of the virtual object as the target sound category characteristics corresponding to the virtual object ( Xu: Page 3, para.[1], page 6, para.[7], during the training of the TTS model, the obtaining unit is configured to obtain the sample image, sample text and label data, the sample image comprises a sample object as a virtual character image, the label data comprises sample voice of the sample object corresponding to the sample text. The virtual character image in the target image can be the image of human, such as short hair, adult female or the virtual character image in the target image also can be a cartoon image ( object category));
( Xu: Page 6, para.[2], obtaining the target image and target text for speech synthesis, the target image comprises a target object as a virtual character. Page 6, para.[5], generating a virtual character corresponding to the sound feature);
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Xu’s teaching of voice synthesis method and model training method, into the system and method of video display and processing method, apparatus and system, in the field of multimedia technology, taught by Chen, because, this would improve the diversity and flexibility of man-machine voice interaction.(Xu, Page 3).
Regarding Claim 8, Chen in view of Xu teach the method of claim 7. Chen further teaches, further comprising: obtaining text information, the text information being used to describe speech content that needs to be output by the virtual object ( Chen: Para.[0251], obtaining subtitle text for the virtual character object which will broadcast the subtitle text ( such as news broadcast));
Xu further teaches, and generating speech data with the target sound category characteristics for the virtual object based on the text information ( Xu: page 6, para.[10], sound feature of the target object and the target text of the to-be-synthesized speech input training speech synthesis model, to obtain the target speech of the sound characteristic of the target object output by the speech synthesis model ).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Xu’s teaching of voice synthesis method and model training method, into the system and method of video display and processing method, apparatus and system, in the field of multimedia technology, taught by Chen, because, this would improve the diversity and flexibility of man-machine voice interaction.(Xu, Page 3).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NADIRA SULTANA whose telephone number is (571)272-4048. The examiner can normally be reached M-F,7:30 am-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, Paras D. Shah can be reached on (571) 270-1650. 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.
/NADIRA SULTANA/Examiner, Art Unit 2653
/Paras D Shah/Supervisory Patent Examiner, Art Unit 2653
06/19/2026
Prosecution Insights