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 § 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) 1-5, 7 and 10 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Wang et al. (U.S. Patent No. 10,504,511, hereinafter “Wang”).
In regard to claim 1, Wang discloses a method for performing wake-up control on a voice-controlled device with aid of detecting voice feature of self-defined word, the method comprising:
during a registration phase among multiple phases, performing feature collection on audio data of at least one audio clip to generate at least one feature list of the at least one audio clip, in order to establish a feature-list-based database in the voice-controlled device (a wake-up model including a plurality of features is generated based on a user’s utterance of a wake-word, column 6, lines 47-65), wherein the at least one audio clip carries at least one self-defined word (the wake-up word is a user customized word, column 6, lines 13-28), the feature-list-based database comprises the at least one feature list (the models comprising features are stored in a command store, column 6, lines 63-65), any feature list among the at least one feature list comprises multiple features of a corresponding audio clip among the at least one audio clip (the model is updated with additional utterances of the wake-up command, column 6, lines 61-63), and the multiple features respectively belong to multiple predetermined types of features (features include a plurality of types of features, column 6, lines 55-61);
during an identification phase among the multiple phases, performing the feature collection on audio data of another audio clip to generate another feature list of the other audio clip (features are extracted from a user’s voice input to determine whether a wake-up utterance was received, column 3, lines 24-52); and
during the identification phase, performing at least one screening operation on at least one feature in the other feature list according to the feature-list-based database to determine whether the other audio clip is invalid, in order to selectively ignore the other audio clip or execute at least one subsequent operation, wherein the at least one subsequent operation comprises waking up the voice-controlled device (when a wake-up detection module detects a wake-up utterance, only if the wake-up utterance was spoken by the authorized user, a wake-up command is executed, column 3, lines 46-63).
In regard to claim 2, Wang discloses the at least one audio clip comprises multiple audio clips, and the at least one feature list comprises respective feature lists of the multiple audio clips, wherein the any feature list among the at least one feature list represents a feature list among the respective feature lists of the multiple audio clips, and the corresponding audio clip represents one of the multiple audio clips (the model comprises features representing characteristics of multiple utterances of the wake-up command, column 6, lines 47-65).
In regard to claim 3, Wang discloses performing the at least one screening operation on the at least one feature in the other feature list according to the feature-list-based database to determine whether the other audio clip is invalid in order to selectively ignore the other audio clip or execute the at least one subsequent operation further comprises:
if the other audio clip is invalid, ignoring the other audio clip (a wake-up command is executed only if the wake-up utterance was spoken by the authorized user, column 3, lines 46-63); and
if the other audio clip is not invalid, executing the at least one subsequent operation (if the wake-up utterance was spoken by the authorized user, the wake-up command is executed, column 3, lines 46-63).
In regard to claim 4, Wang discloses the at least one audio clip comprises at least one first audio clip of a first user and comprises at least one second audio clip of a second user (different users configure different wake-up utterances, column 6, lines 29-46); and performing the feature collection on the audio data of the at least one audio clip to generate the at least one feature list of the at least one audio clip further comprises:
performing the feature collection on first audio data of the at least one first audio clip to generate at least one first feature list of the at least one first audio clip, wherein each first audio clip among the at least one first audio clip carries a first self-defined word, the feature-list-based database comprises the at least one first feature list, any first feature list among the at least one first feature list comprises multiple first features of a corresponding first audio clip among the at least one first audio clips, and the multiple first features respectively belong to the multiple predetermined types of features (multiple utterances of a first user speaking a customized wake-up command are analyzed to determine features representing characteristics of the user’s utterances of the wake-up command and stored as a model, column 6, lines 29-65); and
performing the feature collection on second audio data of the at least one second audio clip to generate at least one second feature list of the at least one second audio clip, wherein each second audio clip among the at least one second audio clip carries a second self-defined word, the feature-list-based database comprises the at least one second feature list, any second feature list among the at least one second feature list comprises multiple second features of a corresponding second audio clip among the at least one second audio clip, and the multiple second features respectively belong to the multiple predetermined types of features (multiple utterances of a second user speaking a customized wake-up command are analyzed to determine features representing characteristics of the user’s utterances of the wake-up command and stored as a model, column 6, lines 29-65).
In regard to claim 5, Wang discloses by performing machine learning, a predetermined classifier corresponding to at least one predetermined model is established in the voice-controlled device (a wake-up utterance model and voiceprint is established, column 6, line 47 to column 7, line 8); the at least one feature in the other feature list is at least one of all features in the other feature list, wherein said all features in the other feature list respectively belong to the multiple predetermined types of features (the same features are extracted in both the registration phase and the identification phase, column 3, line 64 to column 4, line 14 and column 6, line 66 to column 7, line 8); and the at least one subsequent operation further comprises:
utilizing the predetermined classifier to perform machine-learning-based classification according to said all features in the other feature list to determine whether a speaker of the other audio clip is a first user or a second user, in order to selectively execute at least one first action corresponding to the first user or at least one second action corresponding to the second user (based on the determined wake-up utterance and determined user identity, the device determines whether a first user wake-up command or a second user wake-up command was received, column 3, line 34 to column 4, line 14 and column 6, lines 29-46).
In regard to claim 7, Wang discloses performing the at least one screening operation on the at least one feature in the other feature list according to the feature-list-based database to determine whether the other audio clip is invalid in order to selectively ignore the other audio clip or execute the at least one subsequent operation further comprises:
performing the at least one screening operation on the at least one feature in the other feature list according to the feature-list-based database to determine whether the other audio clip is invalid, in order to selectively ignore the other audio clip or execute the at least one subsequent operation, having no need to link to any cloud database through any network to obtain any speech data for determining which words the at least one self-defined word includes (see Fig. 3, during the screening operation, command hub 104 receives a voice input 304 and determines whether or not to execute the wake up operation 310 without any contact of cloud service 200, column 9, line 31 to column 10, line 1).
In regard to claim 10, Wang discloses a processing circuit, for performing wake-up control on a voice-controlled device with aid of detecting voice feature of self-defined word (Fig. 4, 400), the processing circuit comprising:
multiple processing modules, arranged to perform operations of the processing circuit (at least one processor 402, column 10, lines 32-41), wherein the multiple processing modules comprise:
a feature list processing module, arranged to perform feature-list-related processing (at least one processor 402, column 10, lines 32-41); and
at least one other processing module, arranged to perform feature collection (I/O interface 414, column 10, lines 32-41);
wherein:
during a registration phase among multiple phases, the processing circuit performs the feature collection on audio data of at least one audio clip to generate at least one feature list of the at least one audio clip, in order to establish a feature-list-based database in the voice-controlled device (a wake-up model including a plurality of features is generated based on a user’s utterance of a wake-word, column 6, lines 47-65), wherein the at least one audio clip carries at least one self-defined word (the wake-up word is a user customized word, column 6, lines 13-28), the feature-list-based database comprises the at least one feature list (the models comprising features are stored in a command store, column 6, lines 63-65), any feature list among the at least one feature list comprises multiple features of a corresponding audio clip among the at least one audio clip (the model is updated with additional utterances of the wake-up command, column 6, lines 61-63), and the multiple features respectively belong to multiple predetermined types of features (features include a plurality of types of features, column 6, lines 55-61);
during an identification phase among the multiple phases, the processing circuit performs the feature collection on audio data of another audio clip to generate another feature list of the other audio clip (features are extracted from a user’s voice input to determine whether a wake-up utterance was received, column 3, lines 24-52); and
during the identification phase, the processing circuit performs at least one screening operation on at least one feature in the other feature list according to the feature-list-based database to determine whether the other audio clip is invalid, in order to selectively ignore the other audio clip or execute at least one subsequent operation, wherein the at least one subsequent operation comprises waking up the voice-controlled device (when a wake-up detection module detects a wake-up utterance, only if the wake-up utterance was spoken by the authorized user, a wake-up command is executed, column 3, lines 46-63).
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) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang, in view of Scikit-learn (Getting Started).
In regard to claim 6, Wang is silent as to the dimensions of the model.
Scikit-learn disclose that for any machine learning model, a dimension of a predetermined space of the at least one predetermined model is equal to a feature-type count of the multiple predetermined types of features (a model’s input dimensions are defined by the number of features of the data, see “Fitting and predicting: estimator basics” section).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to make the dimension of a predetermined space of the at least one predetermined model equal to a feature-type count of the multiple predetermined types of features, because, as is notoriously well-known in the art, the input dimensions of a machine learning model must typically match the number of features contained in the data.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wang, in view of Femal (U.S. Patent No. 9,467,569).
In regard to claim 8, Wang does not disclose any voice activity detection steps.
Femal discloses a method for detecting voice activity in an input signal, wherein performing the feature collection on the audio data of the at least one audio clip to generate the at least one feature list of the at least one audio clip further comprises:
after recording the corresponding audio clip to obtain corresponding audio data of the corresponding audio clip, analyzing first audio data of a first partial audio clip of the corresponding audio clip to determine an energy threshold and a zero-crossing rate threshold according to multiple first audio frames of the first audio data, for further processing remaining audio data of a remaining partial audio clip of the corresponding audio clip (a voice quality index (VQI) is calculated based on energy and zero-crossing (ZCR) measurements and thresholds for detecting voice activity are adjusted, column 5, line 46 to column 6, line 41); and
analyzing the remaining audio data of the remaining partial audio clip to calculate respective energy values and zero-crossing rates of multiple second audio frames of the remaining audio data, and determining, according to whether an energy value of any second audio frame among the multiple second audio frames reaches the energy threshold and whether a zero-crossing rate of the any second audio frame reaches the zero-crossing rate threshold, that a voice type of the any second audio frame is one of multiple predetermined voice types, for determining the multiple features of the corresponding audio clip according to respective voice types of the multiple second audio frames (the short term energy of the audio signal is compared to an energy threshold, column 7, lines 36-42; the zero crossing rate of the audio signal is compared to a zero crossing rate threshold, column 8, line 57 to column 9, line 28; and based on the measurements the audio signal is classified as active voice or noise, column 9, lines 29-50).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to determine voice activity using short term energy and zero crossing rates, because it would allow the method to accurately differentiate noise from speech, as taught by Femal (column 4, lines 40-43).
Allowable Subject Matter
Claim 9 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.
The following is a statement of reasons for the indication of allowable subject matter:
The subject matter of claim 9 is illustrated in Fig. 7 of the specification, wherein a beginning audio segment of an audio clip comprising at least the multiple first audio frames (used to determine the energy threshold and zero-crossing rate threshold, labeled “Supposed to be noise” in Fig. 7) is designated as a first predetermined type (Seg1 designated as Unvoiced in Fig. 7). The audio clip is further divided into multiple segments according to the respective voice types of multiple second audio frames wherein any two adjacent audio frames having a same predetermined voice type among all audio frames of the corresponding audio data belong to a same audio segment (Seg2-Seg9 in Fig. 7). Claim 9 then further requires calculating a total time length of at least one main audio segment among the multiple audio segments to be a feature among the multiple features of the corresponding audio clip, and calculating at least one segment-level parameter of each audio segment corresponding to a second predetermined voice type among the multiple audio segments to determine at least one parameter of the corresponding audio clip according to the at least one segment-level parameter to be at least one other feature among the multiple features of the corresponding audio clip.
While Femal and the additional prior art of record generally disclose dividing an audio clip according to adjacent frames having the same type, the prior art of record do not disclose or suggest the additional specific steps recited in claim 9 for calculating at least one segment-level parameter of each audio segment corresponding to a second predetermined voice type.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Sun et al., Stoimenov et al., Rifkin, Phipps et al., Panda et al., Kim et al., Himmelstein, Kaushik et al., Chen, and Binder et al. disclose additional methods allowing users to customize wake-up words and/or evaluating speech features.
Sung et al. and Duni et al. disclose additional methods of voice detection using energy and zero crossing rate.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRIAN LOUIS ALBERTALLI whose telephone number is (571)272-7616. The examiner can normally be reached M-F 8AM-3PM, 4PM-5PM.
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, Bhavesh Mehta can be reached at 571-272-7453. 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.
BLA 6/8/26
/BRIAN L ALBERTALLI/ Primary Examiner, Art Unit 2656
Prosecution Insights