Prosecution Insights
Last updated: November 18, 2026
Application No. 18/794,702

DISTINGUISHING USER SPEECH FROM BACKGROUND SPEECH IN SPEECH-DENSE ENVIRONMENTS

Non-Final OA §103
Filed
Aug 05, 2024
Priority
Jul 27, 2016 — continuation of 10/714,121 +4 more
Examiner
YANG, QIAN
Art Unit
2677
Tech Center
2600 — Communications
Assignee
Vocollect Inc.
OA Round
3 (Non-Final)
74%
Grant Probability
Favorable
3-4
OA Rounds
99%
With Interview

Examiner Intelligence

Grants 74% — above average
74%
Career Allowance Rate
739 granted / 1002 resolved
+11.8% vs TC avg
Strong +31% interview lift
Without
With
+31.0%
Interview Lift
resolved cases with interview
Typical timeline
Avg Prosecution
23 currently pending
Career history
1030
Total Applications
across all art units

Office Action

§103
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 . Continued Examination Under 37 CFR 1.114 A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on September 1, 2026 has been entered. Response to Amendment Applicant's amendment filed on September 1, 2026 has been entered. Claims 1, 8 and 15 have been amended. Claims 4 and 11 have been canceled. No claims have been added. Claims 1 – 3, 5 – 10 and 12 – 20 are still pending in this application, with claims 1, 8 and 15 being independent. Response to Arguments Applicant’s arguments with respect to claim(s) 1 – 3, 5 – 10 and 12 – 20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. 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) 1, 5 – 8 and 12 – 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Braho et al. (US Patent Application Publication 2014/0278391), hereinafter referred as Braho, in view of El Dokor et al. (US Patent Application Publication 2014/0277936), hereinafter referred as El Dokor, and in further view of Grokop et al. (WIPO Patent Application Publication WO 2013/040414), hereinafter referred as Grokop. Regarding claim 8, Braho discloses a speech recognition device (SRD) for use in warehouse picking operations (Figs. 1 - 3) comprising: a microphone (Fig. 1, #120a, 120b); at least one processor (Fig. 2, #214); and at least one memory (Fig. 2, #218, 220) including computer program code, the at least one memory and the computer program code configured to, with the at least one processor, cause the SRD to at least: receive, at the microphone, an audio input (Fig. 5, 504, [0110]), wherein the audio input is related to a phrase uttered to an instruction to pick an item, and an identification of at least of a location and an object ([0007], “the user may receive voice instructions, …, and/or receive directions such as location information specifying locations for picking up or delivering goods”); classify a portion of the received audio input, wherein the portion of the received audio input is classified as user speech (Fig. 9, 909 - 910, [0157 - 0160]); detect background noise in the portion of the received audio input classified as the user speech ([0161], selectively adjust threshold(s) … distinctions between being classified as speech versus a non-transient background noise versus a transient noise event); and in response to determining that the detected background noise exceeds a predetermined threshold, reject the portion of the received audio input that is classified as the user speech ([0161], selectively adjust threshold(s) used by an accept/reject module for accepting or rejecting a word of a hypothesis from the decoder … distinctions between being classified as speech versus a non-transient background noise versus a transient noise event). However, Braho fails to explicitly disclose the SRD wherein the audio input is related to a confirmation phrase uttered in response to an instruction wherein the confirmation phrase is at least one of a confirmation of a recognition of a prompt, a confirmation of a completion of a task, or a confirmation of an identification of at least of a location and an object. However, in a similar field of endeavor El Dokor discloses a system of audio input and control ([0025]). In addition, El Dokor discloses the system wherein the audio input is related to a confirmation phrase uttered in response to an instruction wherein the confirmation phrase is at least one of a confirmation of a recognition of a prompt ([0025]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and the audio input is related to a confirmation phrase uttered in response to an instruction wherein the confirmation phrase is at least one of a confirmation of a recognition of a prompt, a confirmation of a completion of a task, or a confirmation of an identification of at least of a location and an object. The motivation for doing this is that audio input can be confirmed without an error so that process can be more accurate. However, Braho in view of El Dokor fails to explicitly disclose the SRD wherein classify portions of the received audio input based on a machine learning model, wherein the machine learning model is trained using a training corpus comprising user speech and background noise. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classify portions of the received audio input is based on a machine learning model ([0046 – 0048]), wherein the machine learning model is trained using a training corpus comprising user speech and background noise ([0047], “the classifier can be trained using positive examples of speech combined with various types of environmental noise at a range of SNRs (e.g., -3dB to +30dB)”). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and classify portions of the received audio input is based on a machine learning model, wherein the machine learning model is trained using a training corpus comprising user speech and background noise. The motivation for doing this is to increase ability to automatically learn complex acoustic patterns from data and accurately categorize audio in noisy, real-world environments. Regarding claim 12 (depends on claim 8), Braho discloses the SRD further comprising a headset, wherein the microphone is mounted on the headset and is configured for use in a warehouse environment (Fig. 1, #120a and 120b). Regarding claim 13 (depends on claim 8), Braho discloses the SRD wherein the classification is processing based on a corpus comprising at least one word and phrase related to the warehouse picking operations ([0007], “the user may receive voice instructions, …, and/or receive directions such as location information specifying locations for picking up or delivering goods”). However, Braho in view of El Dokor fails to explicitly disclose the SRD wherein the classification is based on the machine learning model that is trained based on a training corpus comprising at least one word and phrase. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classify portions of the received audio input is based on a machine learning model ([0046 – 0048]), wherein the machine learning model is trained using a training corpus comprising user speech ([0047]). There was some teaching, suggestion, or motivation in Braho and Grokop or in the knowledge generally available to one of ordinary skill in the art, to modify the reference or to combine reference teachings to achieve the claimed limitations; and there was reasonable expectation of success to achieve the claimed limitations (KSG scenario G). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and the classification is based on the machine learning model that is trained based on a training corpus comprising at least one word and phrase. The motivation for doing this is that the device of Braho can be more powerful and advanced for artificial intelligence. Regarding claim 14 (depends on claim 13), Braho discloses the SRD wherein the classification is processing based on a corpus and the audio input received during the warehouse picking operations ([0007], “the user may receive voice instructions, …, and/or receive directions such as location information specifying locations for picking up or delivering goods”; Fig. 1, [0046 - 0053]). However, Braho in view of El Dokor fails to explicitly disclose the SRD wherein the classification is based on the machine learning model that is trained based on training corpus and the audio input. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classification is based on the machine learning model that is trained based on training corpus and the audio input ([0046 - 0048]). There was some teaching, suggestion, or motivation in Braho and Grokop or in the knowledge generally available to one of ordinary skill in the art, to modify the reference or to combine reference teachings to achieve the claimed limitations; and there was reasonable expectation of success to achieve the claimed limitations (KSG scenario G). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and the classification is based on the machine learning model that is trained based on training corpus and the audio input. The motivation for doing this is that the device of Braho can be more powerful and advanced for artificial intelligence. Regarding claims 1 and 5 – 7, they are corresponding to claims 8 and 12 – 14, respectively, thus, they are interpreted and rejected for a same reason set forth for claims 8 and 12 – 14. Claim(s) 2 – 3, 9 and 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over Braho in view of El Dokor, in further view of Grokop, and Yen et al. (US Patent Application Publication 2009/0271187), hereinafter referred as Yen. Regarding claim 9 (depends on claim 8), Braho discloses the SRD wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the SRD to at least classify a portion of the received audio input as background noise and reject the other portion of the received audio input that is classified as the background noise ([0161 – 0162]). However, Braho in view of El Dokor fails to explicitly disclose the SRD wherein classify another portion of the received audio input is based on the machine learning model; and background noise is background speech. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classify portions of the received audio input is based on a machine learning model ([0046 – 0048]). In a similar field of endeavor Yen discloses a system of audio signal processing (abstract). In addition, Yen discloses the system wherein background noise is background speech ([0057]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and classify portions of the received audio input is based on a machine learning model; and background noise is background speech. The motivation for doing this is that the device of Braho can be more powerful and advanced for artificial intelligence, and a specific type of background noise can be rejected so that the Application of Braho can be extended. Regarding claim 10 (depends on claim 8), Braho discloses the SRD wherein the classification is to distinguish the user speech from background noise ([0161 – 0162]). However, Braho in view of El Dokor fails to explicitly disclose the machine learning model is at least one of a neural network system, a support vector machine, and an inductive logic system and wherein the machine learning model is trained to distinguish user speech from background speech. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classification is based on a machine learning model is at least one of a neural network system, a support vector machine, and an inductive logic system and wherein the machine learning model is trained to distinguish sounds ([0046 - 0048]). In a similar field of endeavor Yen discloses a system of audio signal processing (abstract). In addition, Yen discloses the system wherein background noise is background speech ([0057]). There was some teaching, suggestion, or motivation in Braho, Grokop and Yen or in the knowledge generally available to one of ordinary skill in the art, to modify the reference or to combine reference teachings to achieve the claimed limitations; and there was reasonable expectation of success to achieve the claimed limitations (KSG scenario G). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and the machine learning model is at least one of a neural network system, a support vector machine, and an inductive logic system and wherein the machine learning model is trained to distinguish user speech from background speech. The motivation for doing this is that the device of Braho can be more powerful and advanced for artificial intelligence, and a specific type of background noise can be rejected so that the Application of Braho can be extended. Regarding claims 2 – 3, they are corresponding to claims 9 – 10, respectively, thus, they are interpreted and rejected for a same reason set forth for claims 9 – 10. Claim(s) 15 – 16 and 18 – 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Braho in view of Grokop. Regarding claim 15, Braho discloses a method of speech recognition for use in warehouse picking operations (abstract), the method comprising: receiving, by a processor, an audio input (Fig. 5, 504, [0110]); classifying, by the processor, a portion of the received audio input, wherein the portion of the received audio input is classified as user speech (Fig. 9, 909 - 910, [0157 - 0160]) related to the warehouse picking operations ([0007], “the user may receive voice instructions, …, and/or receive directions such as location information specifying locations for picking up or delivering goods”); detect, by the processor, background noise in the portion of the received audio input classified as the user speech ([0161], selectively adjust threshold(s) … distinctions between being classified as speech versus a non-transient background noise versus a transient noise event); and rejecting, by the processor, the portion of the received audio input that is classified as the user speech in response to the detected background noise exceeding a predetermined threshold of the detected background noise ([0161], selectively adjust threshold(s) used by an accept/reject module for accepting or rejecting a word of a hypothesis from the decoder … distinctions between being classified as speech versus a non-transient background noise versus a transient noise event); and processing, by the processor, a remaining portion of the received audio input that is classified as user speech (Fig. 5, 518, [0119], “This may advantageously limit the information being sent to be information which has been classified (i.e., determined to likely be) as speech rather than noise”) to generate at least one of words and phrases related to the warehouse picking operations (Fig. 5, 520 - 522, [0120 - 0122], “digitized audio to recognize speech”; [0162], “outputs recognized text”; [0007]). However, Braho fails to explicitly disclose the method wherein classifying the portion of the received audio input based on a machine learning model, wherein the machine learning model is trained using a training corpus comprising user speech and background noise. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classify portion of the received audio input is based on a machine learning model ([0046 – 0048]), wherein the machine learning model is trained using a training corpus comprising user speech and background noise ([0047], “the classifier can be trained using positive examples of speech combined with various types of environmental noise at a range of SNRs (e.g., -3dB to +30dB)”). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and classify portion of the received audio input is based on a machine learning model, wherein the machine learning model is trained using a training corpus comprising user speech and background noise. The motivation for doing this is to increase ability to automatically learn complex acoustic patterns from data and accurately categorize audio in noisy, real-world environments. Regarding claim 16 (depends on claim 15), Grokop discloses the method wherein the machine learning model is at least one of a neural network system, a support vector machine, and an inductive logic system ([0046]). Regarding claim 18 (depends on claim 15), Braho discloses the method further comprising a microphone, wherein the microphone is mounted on a headset and is configured for use in a warehouse environment (Fig. 1, #120a and 120b). Regarding claim 19 (depends on claim 15), Braho discloses the method wherein the detected background noise comprises at least one of an operation of a vehicle in a warehouse and a movement of pallets in the warehouse ([0005], driving a vehicle). Regarding claim 20 (depends on claim 15), Braho discloses the method wherein the classification is processing based on a corpus comprising at least one word and phrase related to the warehouse picking operations ([0007], “the user may receive voice instructions, …, and/or receive directions such as location information specifying locations for picking up or delivering goods”). However, Braho fails to explicitly disclose the method wherein the classification is based on the machine learning model that is trained based on a training corpus comprising at least one word and phrase. However, in a similar field of endeavor Grokop discloses a system for speech detection in association with a mobile device (abstract). In addition, Grokop discloses the system wherein the classify portions of the received audio input is based on a machine learning model ([0046 – 0048]), wherein the machine learning model is trained using a training corpus comprising user speech ([0047]). There was some teaching, suggestion, or motivation in Braho and Grokop or in the knowledge generally available to one of ordinary skill in the art, to modify the reference or to combine reference teachings teachings to achieve the claimed limitations; and there was reasonable expectation of success to achieve the claimed limitations (KSG scenario G). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and the classification is based on the machine learning model that is trained based on a training corpus comprising at least one word and phrase. The motivation for doing this is that the device of Braho can be more powerful and advanced for artificial intelligence. Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Braho in view of Grokop, and in further view of El Dokor. Regarding claim 17 (depends on claim 15), Braho fails to explicitly disclose the method wherein the audio input is related to a confirmation phrase, and wherein the confirmation phrase is at least one of a confirmation of a recognition of a prompt, a confirmation of a completion of a task, and a confirmation of an identification of at least of a location and an object. However, in a similar field of endeavor El Dokor discloses a system of audio input and control ([0025]). In addition, El Dokor discloses the audio input is related to a confirmation phrase uttered in response to an instruction wherein the confirmation phrase is at least one of a confirmation of a recognition of a prompt ([0025]). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the invention of Braho, and the audio input is related to a confirmation phrase uttered in response to an instruction wherein the confirmation phrase is at least one of a confirmation of a recognition of a prompt, a confirmation of a completion of a task, and a confirmation of an identification of at least of a location and an object. The motivation for doing this is that audio input can be confirmed without an error so that process can be more accurate. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to QIAN YANG whose telephone number is (571)270-7239. The examiner can normally be reached on Monday-Thursday 8am-6pm. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Bee can be reached on 571-270-5183. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300. 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). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000. /QIAN YANG/ Primary Examiner, Art Unit 2677
Read full office action

Prosecution Timeline

Aug 05, 2024
Application Filed
Feb 06, 2026
Non-Final Rejection mailed — §103
May 06, 2026
Response Filed
May 27, 2026
Final Rejection mailed — §103
Jul 27, 2026
Response after Non-Final Action
Sep 01, 2026
Request for Continued Examination
Sep 08, 2026
Response after Non-Final Action
Sep 23, 2026
Non-Final Rejection mailed — §103 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12784755
INTELLIGENT ASSISTANT FOR HOME AUTOMATION
2y 3m to grant Granted Nov 03, 2026
Patent 12784271
SYSTEMS AND METHODS FOR AUGMENTED REALITY
2y 1m to grant Granted Nov 03, 2026
Patent 12777132
INTELLIGENT VIDEO SURVEILLANCE SYSTEM AND METHOD
2y 3m to grant Granted Oct 27, 2026
Patent 12770373
METHOD AND SYSTEM FOR GENERATING A DETECTOR FOR PROCESS MONITORING
3y 4m to grant Granted Oct 20, 2026
Patent 12770285
METHOD AND SYSTEM FOR LIVESTOCK MONITORING AND MANAGEMENT
2y 10m to grant Granted Oct 20, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
74%
Grant Probability
99%
With Interview (+31.0%)
High
PTA Risk
Based on 1002 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month