Notice of Pre-AIA or AIA Status
1. 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
2. Applicant's arguments filed 02/12/2026 have been fully considered but they are not persuasive. Applicant argues that the combination of Jiang and Tomashenko fails to disclose determine, using a speech rate classification machine learning network, a speech rate classification corresponding to the audio sample, the speech rate classification included in a plurality of speech rate classifications associated with the speech rate classification machine learning network;
obtain, from information embedded in machine learning model metadata of the speech rate classification machine learning network, a spoken length value corresponding to the spoken keyword and the speech rate classification, wherein the information is indicative of a respective spoken length value of the spoken keyword for at least one speech rate classification of the plurality of speech rate classifications.
The Examiner respectfully disagrees. Jiang explicitly discloses storing average keyword length values (e.g., phoneme duration tables) used for keyword boundary refinement (see Jiang, Col 5). These stored values are model parameters used by the system during operation, i.e., information embedded in the model or its associated configuration. Tomashenko further discloses that speech rate is classified using a neural network (see Tomashenko, Introduction) and that average phoneme/triphone durations are normalized based on speech rate classifications (see Tomashenko section 2). Therefore, teaching that duration values are conditioned on speech rate categories (slow, normal, fast). The combination therefore altogether teaches: storing average duration and length information (Jiang) and selecting or adjusting such duration information based on speech rate classification (Tomashenko). Which together reasonably correspond to using a speech rate classification machine learning network, a speech rate classification corresponding to the audio sample, the speech rate classification included in a plurality of speech rate classifications associated with the speech rate classification machine learning network; and
obtain, from information embedded in machine learning model metadata of the speech rate classification machine learning network, a spoken length value corresponding to the spoken keyword and the speech rate classification, wherein the information is indicative of a respective spoken length value of the spoken keyword for at least one speech rate classification of the plurality of speech rate classifications.
Applicant arguments appear to improperly attack Jiang and Tomashenko individually. However, the rejection relies on their combination, where Tomashenko explicitly provides the missing link between duration values and speech rate classifications. Further, the claimed model metadata does not impose any structural limitation, or additional pipeline beyond storing or associating parameters used by the model. Jiang’s stored phoneme duration tables and parameters used in keyword boundary refinement would have been understood by one of ordinary skill in the art as part of the model configuration or metadata.
Accordingly, claims 1 and 19 being rejected over the combination of Jiang in view of Tomashenko is maintained.
Claim Rejections - 35 USC § 103
3. 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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
4. Claims 1-2, 4-20 and 22-30 are rejected under 35 U.S.C. 103 as being unpatentable over Jiang et al. (US 10,074,363) (herein Jiang) in view of Tomashenko et al. “Speaking Rate Estimation Based on Deep Neural Networks” (herein Tomashenko).
Regarding Claim 1:
Jiang discloses an apparatus for processing one or more audio samples, comprising:
one or more memories configured to store the one or more audio samples (Jiang: Col 1:40-53 discloses an apparatus with memory to store audio instructions for processing it);
and one or more processors coupled to the one or more memories (Jiang: Col 1:40-53 discloses a processor to execute audio speech recognition) the one or more processors being configured to:
detect, using a first keyword detection model, a spoken keyword within an audio sample of the one or more audio samples (Jiang: Col 2: 36-67 Jiang explicitly discloses it performs keyword spotting by matching keyword phoneme patterns to audio derived phoneme image maps);
determine estimated keyword indices corresponding to detection of the spoken keyword within the audio sample, the estimated keyword indices comprising an estimated keyword start index and an estimated keyword end index (Jiang: Col 2:46-48 discloses general search stage produces starting and ending key word boundaries);
obtain, from information embedded in machine learning model metadata of the speech rate classification machine learning network, a spoken length value corresponding to the spoken keyword (Jiang: Col 5: discloses building keyword length from stored phoneme from stored phoneme duration constraints for the constituent phonemes of the keyword, i.e., spoken length value corresponding to the spoken keyword)
and generate refined keyword indices based on the estimated keyword indices and the spoken length value, wherein the refined keyword indices include a refined keyword start index shifted to a time earlier than the estimated keyword start index (Jiang: Col 2:48-53 discloses moving the keyword boundary earlier if the detected start point is late, i.e., it shifts the start boundary earlier based on phoneme duration, energy cues etc.).
Jiang does not explicitly disclose:
determine, using a speech rate classification machine learning network, a speech rate classification corresponding to the audio sample, the speech rate classification included in a plurality of speech rate classifications associated with the speech rate classification machine learning network;
a spoken length value corresponding to the spoken keyword and the speech rate classification, wherein the information is indicative of a respective spoken length value of the spoken keyword for at least one speech rate classification of the plurality of speech rate classifications;
However, Tomashenko discloses:
determine, using a speech rate classification machine learning network, a speech rate classification corresponding to the audio sample, the speech rate classification included in a plurality of speech rate classifications associated with the speech rate classification machine learning network (Tomashenko: Introduction and Section 3, explicitly teach a deep neural network (DNN) trained to classify speech into slow, medium and fast or silence, i.e., a plurality of speech rate classifications associated with the machine learning network);
obtain, from information embedded in machine learning model metadata of the speech rate classification machine learning network, a spoken length value corresponding to the spoken keyword and the speech rate classification, wherein the information is indicative of a respective spoken length value of the spoken keyword for at least one speech rate classification of the plurality of speech rate classifications (Tomashenko: Section 2 discloses normalization on the average length of triphones computed from the training database and defines speaking rate classes slow, medium and fast, thus Tomashenko teaches information associated with the speech rate classification machine learning network that is indicative of respective spoken length value for at least one speech rate classification of a plurality of speech rate classification.
Examiner Interpretation {Jiang provides a baseline spoken length value of the spoken keyword using stored phoneme duration tables. Tomashenko teaches that such expected durations are classified and normalized according to speech rate, including average triphone lengths associated with speech rate class classes. A person of ordinary skill in the art would have understood such stored class associated duration values to constitute information embedded in machine learning model metadata or model associated configuration data used during inference});
It would have been obvious for one of ordinary skill in the art before the affective filing date of the claimed invention to modify Jiang’s keyword boundary refinement process to incorporate the speaking-rate normalization taught in Tomashenko. Both are within the same field of endeavor, audio speech recognition and disclose methods for understanding keywords and phrases better within a user utterance. Jiang already relies on phoneme triphone average duration statistics to refine keyword start and end boundaries. Tomashenko teaches that speaking rate is a primary source of duration variability and further teaches normalizing average triphone durations according to measured speech rate (see Section 2 of Tomashenko). The motivation for doing so is disclosed in Tomashenko’s Introduction “A reliable estimation of speaking rate is often needed in order to adapt the ASR system to variations in speaking rate.” Therefore, the combination yields no change in overall system operation and merely applies a known adjustment (rate normalization) to an existing duration-based boundary refinement method.
Regarding Claim 2:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, wherein the speech rate classification is indicative of a slow speech rate classification, a normal speech rate classification, or a fast speech rate classification for the spoken keyword within the audio sample (Tomashenko: Section 3 discloses training the DNN model to output slow, normal, fast. These outputs directly correspond to the speech rate information).
It would have been obvious for one of ordinary skill in the art before the affective filing date of the claimed invention to incorporate Tomashenko’s keyword speech rate classification into Jiang. Both are within the same field of endeavor, audio speech recognition and disclose methods for understanding keywords and phrases better within a user utterance. Tomashenko expressly classifies speech rate into slow, normal and fast categories. Claim 1 already recites determining speech rate which is taught using the model of Tomashenko, representing the speech rate information as one of these explicit categories is taught by the prior art already and would equate to a simple modification of Jiang’s base structure without undue experimentation. The motivation for doing so is disclosed in Tomashenko’s Introduction “A reliable estimation of speaking rate is often needed in order to adapt the ASR system to variations in speaking rate.”
Regarding Claim 4:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, wherein the one or more processors are configured to:
determine the speech rate classification using the speech rate classification machine learning network in response to detection of the spoken keyword (Tomashenko: Section 1 and 3 teaches computing speech rate for a target speech segment, including per word and per phone duration normalization using its overall machine learning architecture based on Deep learning networks and other formulas embedded into this process);
and determine the estimated keyword start index using a keyword start estimation neural network in response to detection of the spoken keyword (Jiang: Col 2:25-65 and Col 4:14-40 explicitly performs refinement after a keyword has been detected which includes start and end boundary using phoneme durations and voicing cues using a deep neural network based acoustic triphone model).
It would have been obvious for one of ordinary skill in the art before the affective filing date of the claimed invention to modify Jiang’s keyword boundary refinement process to incorporate the speaking-rate normalization taught in Tomashenko. Both are within the same field of endeavor, audio speech recognition and disclose methods for understanding keywords and phrases better within a user utterance. Jiang already relies on phoneme triphone average duration statistics to refine keyword start and end boundaries. Tomashenko teaches that speaking rate is a primary source of duration variability and further teaches normalizing average triphone durations according to measured speech rate (see Section 2 of Tomashenko). The motivation for doing so is disclosed in Tomashenko’s Introduction “A reliable estimation of speaking rate is often needed in order to adapt the ASR system to variations in speaking rate.” Therefore, the combination yields no change in overall system operation and merely applies a known adjustment (rate normalization) to an existing duration-based boundary refinement method.
Regarding Claim 5:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 4, wherein: the first keyword detection model and the keyword start estimation neural network are included in a first keyword detection stage of a multi-stage keyword detection system (Jiang: Col 2:25-65 discloses a multi stage keyword detection stage and a refinement stage that determines start and end boundaries).
Regarding Claim 6:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, wherein:
the first keyword detection model is configured to perform always-on keyword detection for one or more audio samples (Jiang: Col 7:54-60 receives an audio stream, under Broadest Reasonable Interpretation (BRI) this encompasses an always on or lower energy state mode as it is not limited to activation (e.g., pressing a button) because a stream is an ongoing audio from a microphone or live feed, also see the Table in Col 4.);
and the speech rate classification machine learning network is configured to perform speech rate classification for a particular audio sample of the one or more audio samples based on detection of the spoken keyword within the particular audio sample by the first keyword detection model (discloses a classifier that is not run continuously but applied to a selected segment which aligns with running it after keyword detection identifies the region).
It would have been obvious to one of ordinary skill in the art before the effective filing date to disclose non-continuous processing on identified key words. Jian discloses performing continuous keyword detection on streaming audio input to identify occurrences of target keywords. Tomashenko teaches determining speech rate at the word or phoneme segment level, rather than continuously computing duration normalized features over a selected segment. Because continuous speech rate evaluation is computationally expensive and not always necessary when only keyword occurrences are relevant. The motivation for doing so is disclosed in Tomashenko: “DNNs have recently been used with great success in automatic speech recognition tasks [13], and it is interesting to explore their application to the speaking rate estimation problem,” i.e., trying this approach would make the combination predictable and a straightforward improvement.
Regarding Claim 7:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, wherein:
the spoken length value is included in average keyword length information corresponding to the spoken keyword (Jiang: Col 5 table “Apply general duration constraint…” obtains and stores phoneme and keywords duration constraints, which are analogous to average length information per keyword);
and the average keyword length information includes the respective average spoken length value for each speech rate classification the plurality of speech rate classifications associated with the speech rate classification machine learning network (Tomashenko: Section 2, Section 5 results: “A more detailed analysis of changes in the speaking rate is presented in Figure 2, where normalized histograms for relative differences in speaking rate between two adjacent words are shown.” Teaches that phoneme and (which makeup the keywords) durations vary by speech rate class, and that average durations per class are maintained to normalize or adjust alignment boundaries).
It would have been obvious to one of ordinary skill in the art before the effective filing date to disclose Jian discloses performing continuous keyword detection on streaming audio input to identify occurrences of target keywords. Tomashenko teaches determining speech rate at the word or phoneme segment level, and classifying the speech rates. A person of ordinary skill in the art would be able to incorporate the speech rate classification and class-specific duration of Tomashenko into the keyword duration based alignment/refinement of Jiang to improve the accuracy of keyword boundary estimation The motivation for doing so is disclosed in Tomashenko: “the fact that mean durations of different phones and triphones in the database may vary a lot. To get more accurate estimations, we use normalization on the average length of triphones” i.e., trying this approach would make the combination predictable and a straightforward improvement because it improves estimation accuracy.
Regarding Claim 8:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 7, wherein the average keyword length information comprises offline estimations of the respective spoken length values (Jiang: Col 3:1 discloses offline preparation mode).
Regarding Claim 9:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 7, wherein the average keyword length information is included in the information embedded in the machine learning model metadata (Jiang: Col 4:18-32 stores average keyword length values as lookup table / model parameters used by the keyword boundary refinement), and wherein the machine learning model metadata is associated with a configuration of the speech rate classification machine learning network (Jiang: 4:18-32, Col 5 First table, discloses storing average keyword length values as lookup tables and model parameters used by the keyword boundary refinement process, Jiang further discloses in online processing initialization , “loading the phoneme duration table,” loading the keyword pronunciation table,” and “load the triphone lookup table.” This stored duration and lookup information is model associated data loaded prior to inference and used by the keyword boundary refinement process, i.e., machine learning model metadata. ) or a configuration of a keyword indices refinement machine learning network used to generate the refined keyword indices (Examiner Note {the claims are disjunctive hence only meeting the first half of the or statement; the Examiner relies on Tomashenko (see Section 2 and Section 5) for the speech rate classification machine learning network and on Jiang for the recited information being embedded in model associated data used by the keyword indices refinement machine learning network}).
It would have been obvious to one of ordinary skill in the art before the effective filing date to disclose Jian discloses performing continuous keyword detection on streaming audio input to identify occurrences of target keywords. Tomashenko teaches determining speech rate at the word or phoneme segment level, and classifying the speech rates. A person of ordinary skill in the art would be able to incorporate the speech rate classification machine learning parameters of Tomashenko into the keyword duration based alignment/refinement of Jiang to improve the accuracy of keyword boundary estimation The motivation for doing so is disclosed in Tomashenko: “the fact that mean durations of different phones and triphones in the database may vary a lot. To get more accurate estimations, we use normalization on the average length of triphones” i.e., trying this approach would make the combination predictable and a straightforward improvement because it improves estimation accuracy.
Regarding Claim 10:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, wherein, to generate the refined keyword indices, the one or more processors are configured to:
determine an estimated length for the spoken keyword, based on a difference between the estimated keyword end index and the estimated keyword start index (Jiang: Col 4 Table “Finding consecutive frames and log the starting and end points” discloses obtaining a start and end frame indices of the detected keyword and computes durations; Col 5 Confidence score computation discloses the length of the keywords goes from t1 to t2 (a difference between these two is the length));
compare the estimated length to the spoken length value to determine a refined length for the spoken keyword (Jiang: Col 4 Table ”apply general duration constraint: Average frames/phonemes >= 6 Apply individual phoneme duration constraints“ discloses comparing the measured duration of the detected keyword to the expected (average) duration for that keyword and adjusts/refines the segment boundaries accordingly);
and generate the refined keyword indices based on the refined length for the spoken keyword (Jiang: Col 4 Table discloses “if constraints pass… Keyword found and save the timing information” and “refinement… define a word boundary” and Col 2 48-53 “refine and verify the search” teaches after duration comparison and adjustment, the system outputs refined start/end indices).
Regarding Claim 11:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 10, wherein, to generate the refined keyword indices, the one or more processors are configured to:
determine the refined keyword start index as a time index shifted earlier than the estimated keyword start index by a first amount corresponding to a difference between the refined length and the estimated length for the spoken keyword (Jiang: Col 2:48-67 discloses adjusting temporal boundaries based on summed phoneme duration expectations – specifically, extending keyword segments to match expected durations);
and determine a refined keyword end index as a time index shifted later than the estimated keyword end index by a second amount corresponding to the difference between the refined length and the estimated length for the spoken keyword (Jiang: Col 2:48-67 discloses when the detected keyword is shorter than expected, the system moves the start boundary earlier until phoneme and energy constraints match expected keywords).
Regarding Claim 12:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 11, wherein the first amount and the second amount are the same (Jiang: Col 4 Table ”Apply general duration constraint: Average frames/phonemes >= 6 Apply individual phoneme duration constraints.“ The system teaches first applying a general duration adjustment uniformly across the keyword to ensure the average phoneme duration constraint is met which corresponds to adjusting both start and end indices by the same amount).
Regarding Claim 13:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 11, wherein: the first amount comprises a first percentage of the difference between the refined length and the estimated length for the spoken keyword (Jiang: Col 2:48-67 discloses that refinement adjusts keyword boundaries differently depending on phoneme duration and voicing characteristics. This means the system does not always use a fixed uniform shift, but instead assigns different weights (effectively percentages) to boundary adjustments based on how much timing correction is needed. When vowels are longer than consonants the system expands the start boundary more);
and the second amount comprises a second percentage of the difference between the refined length and the estimated length for the spoken keyword (Jiang: Col 2:48-67, Col 5 first table discloses refining the keyword boundary using both phoneme and acoustic boundary cues. Jiang expressly states that a word boundary is identified where the signal exhibits “low energy and low slope.” Low energy and slope occurs after the spoken segment, meaning this feature is used to detect keyword end boundary (cutoff), while phoneme duration influences the total expected time of the spoken keyword).
Regarding Claim 14:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 13, wherein the first percentage is greater than the second percentage (Jiang: Col 5 first Table discloses “Apply individual phoneme duration constraints. Apply voicing constraints. Apply L2-nrom energy and energy slope constraints. Word boundary: low energy and low slope.” The start boundary is adjusted according to phoneme duration, especially vowels which are generally longer meaning more time expansion. The end boundary adjustment uses energy slop which tends to be smaller).
Regarding Claim 15:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 13, wherein the first percentage is greater than 50%, and wherein a sum of the first percentage and the second percentage is equal to 100% (Jiang: Col 4:18-32 refines keyword boundary by first applying phonemic duration constraints to estimate an expected keyword length, and then applying low energy and low slope boundary detection to finalize the word endpoint. Because duration-based refinement determines the majority of the length adjustment through vowel and consonant prediction and energy-slope detection is an end constraint (as explained in the rejection of claims 13 and 14) that only adjusts the tail end of the segment, the proportional contribution of the duration adjustment is necessarily greater than that of the energy based trim. This directly corresponds to the claimed first percentage being greater than the second percentage and the two percentages summing to 100%).
Regarding Claim 16:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, further comprising a microphone configured to obtain the one or more audio samples (Jiang: Fig. 5 user input devices (i.e., microphones)).
Regarding Claim 17:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, further comprising: one or more microphones configured to capture the one or more audio samples for keyword detection (Jiang: Col 9:9-34 the microphone is directly fed into the keyword recognition workflow shown in Fig. 4).
Regarding Claim 18:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 17, wherein the one or more microphones and the first keyword detection model are associated with an always-on keyword detection process implemented by the apparatus (Jiang: Col 7:54-60 receives an audio stream, under Broadest Reasonable Interpretation (BRI) this encompasses an always on or lower energy state mode as it is not limited to activation (e.g., pressing a button) because a stream is an ongoing audio from a microphone or live feed, also see the Table in Col 4.);.
Regarding Claim 19:
Claim 19 has been analyzed with respect to claim 1 and is rejected for the same reasons of obvious as used above.
It is noted that the processors in Jiang used to teach the apparatus of claim 1 perform the method as disclosed in claim 19.
Regarding Claim 20:
Claim 20 has been analyzed with respect to claim 2 and is rejected for the same reasons of obvious as used above.
Regarding Claim 22:
Claim 22 has been analyzed with respect to claim 4 and is rejected for the same reasons of obvious as used above.
Regarding Claim 23:
Claim 23 has been analyzed with respect to claim 5 and is rejected for the same reasons of obvious as used above.
Regarding Claim 24:
Claim 24 has been analyzed with respect to claim 6 and is rejected for the same reasons of obvious as used above.
Regarding Claim 26:
Claim 26 has been analyzed with respect to claim 8 and is rejected for the same reasons of obvious as used above.
Regarding Claim 27:
Claim 27 has been analyzed with respect to claim 9 and is rejected for the same reasons of obvious as used above.
Regarding Claim 28:
Claim 28 has been analyzed with respect to claim 10 and is rejected for the same reasons of obvious as used above.
Regarding Claim 29:
Claim 29 has been analyzed with respect to claim 11 and is rejected for the same reasons of obvious as used above.
Regarding Claim 31:
The proposed combination of Jiang in view of Tomashenko further discloses the processor-implemented method of claim 19, wherein the spoken length value is an average spoken length value corresponding to the spoken keyword (Jiang: 4:18-32, Col 5 First table, discloses obtaining a baseline spoken length value corresponding to the spoken keyword through stored phoneme duration constraints and keyword pronunciation information, further discloses loading the phoneme duration table and the keyword pronunciation table for use in keyword boundary refinement) and the speech rate classification (Tomashenko discloses that speaking rate is classified into a plurality of speech rate classifications, therefore teaching an average spoken length value corresponding to the spoken keyword and the speech rate classification).
It would have been obvious for one of ordinary skill in the art before the affective filing date of the claimed invention to modify Jiang’s keyword boundary refinement process to incorporate the speaking-rate classification in Tomashenko. Both are within the same field of endeavor, audio speech recognition and disclose methods for understanding keywords and phrases better within a user utterance. Jiang already relies on phoneme triphone average duration statistics to refine keyword start and end boundaries. Tomashenko teaches classification according to measured speech rate (see Section 2 of Tomashenko). The motivation for doing so is disclosed in Tomashenko’s Introduction “A reliable estimation of speaking rate is often needed in order to adapt the ASR system to variations in speaking rate.” Therefore, the combination yields no change in overall system operation and merely applies a known adjustment (rate normalization) to an existing duration-based boundary refinement method.
Regarding Claim 32:
Claim 32 has been analyzed with respect to claim 31 and is rejected for the same reasons of obvious as used above.
5. Claims 3 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Jiang, in view of Tomashenko and further in view of Parada San Martin (US 9,715,660).
Regarding Claim 3:
The proposed combination of Jiang and Tomashenko further discloses the apparatus of claim 1, wherein the one or more processors are configured to determine the speech rate classification (Tomashenko: Introduction Page 419, explicitly teaches a deep neural network (DNN) which classifies speech rate from acoustic feature and determine the estimated keyword start index Jiang: Col 2:46-48 discloses general search stage produces starting and ending key word boundaries)
Neither Jiang and Tomashenko explicitly state that this process is done in parallel. However, Parada San Martin discloses processing in parallel (Parada San Martin: Col 17:60 - Col 18:14 discloses that speech/audio analysis systems may perform multiple detection/classification operations in parallel rather than in a strict sequence).
It would have been obvious for one of ordinary skill in the art to disclose processing in parallel for keyword detection systems. The combination of Jiang and Tomashenko are within the same field of endeavor as Parada San Martin, audio speech recognition of keywords. i.e., both disclose processing speech and audio to recognize key or hot-words. The motivation for doing so is “In certain circumstances, multitasking and parallel processing may be advantageous” as discloses by Parada San Martin in Col 17. This shows that depending on the use case parallel processing can be used to reduce processing delay, improving real-time performance and therefore would have been obvious to implement both processes happening in Jiang and Tomashenko in parallel.
Regarding Claim 21:
Claim 21 has been analyzed with respect to claim 3 and is rejected for the same reasons of obvious as used above.
Conclusion
THIS ACTION IS MADE FINAL. 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to IAN SCOTT MCLEAN whose telephone number is (703)756-4599. The examiner can normally be reached "Monday - Friday 8:00-5:00 EST, off Every 2nd Friday".
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, Hai Phan can be reached at (571) 272-6338. 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.
/IAN SCOTT MCLEAN/Examiner, Art Unit 2654
/HAI PHAN/Supervisory Patent Examiner, Art Unit 2654
Prosecution Insights