-
公开(公告)号:US20230027458A1
公开(公告)日:2023-01-26
申请号:US17959734
申请日:2022-10-04
Applicant: Google LLC
Inventor: Rajeev Conrad Nongpiur , Ananya Misra , Chanwoo Kim
Abstract: A method for auralizing a multi-microphone device. Path information for one or more sound paths using dimensions and room reflection coefficients of a simulated room for one of a plurality of microphones included in a multi-microphone device is determined. An array-related transfer functions (ARTFs) for the one of the plurality of microphones is retrieved. The auralized impulse response for the one of the plurality of microphones is generated based at least on the retrieved ARTFs and the determined path information.
-
公开(公告)号:US20240029716A1
公开(公告)日:2024-01-25
申请号:US18480827
申请日:2023-10-04
Applicant: Google LLC
Inventor: Thibault Doutre , Wei Han , Min Ma , Zhiyun Lu , Chung-Cheng Chiu , Ruoming Pang , Arun Narayanan , Ananya Misra , Yu Zhang , Liangliang Cao
CPC classification number: G10L15/063 , G10L15/083 , G10L15/18 , G06N3/045
Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.
-
公开(公告)号:US10412489B2
公开(公告)日:2019-09-10
申请号:US15996070
申请日:2018-06-01
Applicant: Google LLC
Inventor: Rajeev Conrad Nongpiur , Ananya Misra , Chanwoo Kim
Abstract: A method for auralizing a multi-microphone device. Path information for one or more sound paths using dimensions and room reflection coefficients of a simulated room for one of a plurality of microphones included in a multi-microphone device is determined. An array-related transfer functions (ARTFs) for the one of the plurality of microphones is retrieved. The auralized impulse response for the one of the plurality of microphones is generated based at least on the retrieved ARTFs and the determined path information.
-
公开(公告)号:US20220343894A1
公开(公告)日:2022-10-27
申请号:US17348118
申请日:2021-06-15
Applicant: Google LLC
Inventor: Thibault Doutre , Wei Han , Min Ma , Zhiyun Lu , Chung-Cheng Chiu , Ruoming Pang , Arun Narayanan , Ananya Misra , Yu Zhang , Liangliang Cao
Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.
-
公开(公告)号:US11470419B2
公开(公告)日:2022-10-11
申请号:US16555118
申请日:2019-08-29
Applicant: Google LLC
Inventor: Rajeev Conrad Nongpiur , Ananya Misra , Chanwoo Kim
Abstract: A method for auralizing a multi-microphone device. Path information for one or more sound paths using dimensions and room reflection coefficients of a simulated room for one of a plurality of microphones included in a multi-microphone device is determined. An array-related transfer functions (ARTFs) for the one of the plurality of microphones is retrieved. The auralized impulse response for the one of the plurality of microphones is generated based at least on the retrieved ARTFs and the determined path information.
-
公开(公告)号:US20180279043A1
公开(公告)日:2018-09-27
申请号:US15996070
申请日:2018-06-01
Applicant: Google LLC
Inventor: Chanwoo Kim , Rajeev Conrad Nongpiur , Ananya Misra
CPC classification number: H04R3/005 , H04R5/027 , H04R29/005 , H04R29/006 , H04R2201/401 , H04R2430/20
Abstract: A method for auralizing a multi-microphone device. Path information for one or more sound paths using dimensions and room reflection coefficients of a simulated room for one of a plurality of microphones included in a multi-microphone device is determined. An array-related transfer functions (ARTFs) for the one of the plurality of microphones is retrieved. The auralized impulse response for the one of the plurality of microphones is generated based at least on the retrieved ARTFs and the determined path information.
-
公开(公告)号:US11924618B2
公开(公告)日:2024-03-05
申请号:US17959734
申请日:2022-10-04
Applicant: Google LLC
Inventor: Rajeev Conrad Nongpiur , Ananya Misra , Chanwoo Kim
CPC classification number: H04R3/005 , H04R5/027 , H04R29/005 , H04R29/006 , H04R2201/401 , H04R2430/20
Abstract: A method for auralizing a multi-microphone device. Path information for one or more sound paths using dimensions and room reflection coefficients of a simulated room for one of a plurality of microphones included in a multi-microphone device is determined. An array-related transfer functions (ARTFs) for the one of the plurality of microphones is retrieved. The auralized impulse response for the one of the plurality of microphones is generated based at least on the retrieved ARTFs and the determined path information.
-
公开(公告)号:US11804212B2
公开(公告)日:2023-10-31
申请号:US17348118
申请日:2021-06-15
Applicant: Google LLC
Inventor: Thibault Doutre , Wei Han , Min Ma , Zhiyun Lu , Chung-Cheng Chiu , Ruoming Pang , Arun Narayanan , Ananya Misra , Yu Zhang , Liangliang Cao
CPC classification number: G10L15/063 , G06N3/045 , G10L15/083 , G10L15/18
Abstract: A method for training a streaming automatic speech recognition student model includes receiving a plurality of unlabeled student training utterances. The method also includes, for each unlabeled student training utterance, generating a transcription corresponding to the respective unlabeled student training utterance using a plurality of non-streaming automated speech recognition (ASR) teacher models. The method further includes distilling a streaming ASR student model from the plurality of non-streaming ASR teacher models by training the streaming ASR student model using the plurality of unlabeled student training utterances paired with the corresponding transcriptions generated by the plurality of non-streaming ASR teacher models.
-
公开(公告)号:US20190387315A1
公开(公告)日:2019-12-19
申请号:US16555118
申请日:2019-08-29
Applicant: Google LLC
Inventor: Rajeev Conrad Nongpiur , Ananya Misra , Chanwoo Kim
Abstract: A method for auralizing a multi-microphone device. Path information for one or more sound paths using dimensions and room reflection coefficients of a simulated room for one of a plurality of microphones included in a multi-microphone device is determined. An array-related transfer functions (ARTFs) for the one of the plurality of microphones is retrieved. The auralized impulse response for the one of the plurality of microphones is generated based at least on the retrieved ARTFs and the determined path information.
-
-
-
-
-
-
-
-