公开(公告)号：US10140980B2

公开(公告)日：2018-11-27

申请号：US15386979

申请日：2016-12-21

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mirko Visontai ,  Christopher Walter George Thornton ,  Michiel A. U. Bacchiani ,  Tara N. Sainath ,  Ehsan Variani ,  Izhak Shafran

IPC: G10L15/16 ,  G10L19/02 ,  G10L15/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

公开(公告)号：US20180174575A1

公开(公告)日：2018-06-21

申请号：US15386979

申请日：2016-12-21

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mirko Visontai ,  Christopher Walter George Thornton ,  Michiel A.U. Bacchiani ,  Tara N. Sainath ,  Ehsan Variani ,  Izhak Shafran

IPC: G10L15/16 ,  G10L19/02 ,  G10L15/02

CPC classification number: G10L15/16 ,  G10H1/00 ,  G10H2210/036 ,  G10H2210/046 ,  G10H2250/235 ,  G10H2250/311 ,  G10L15/02 ,  G10L17/18

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

公开(公告)号：US20200286468A1

公开(公告)日：2020-09-10

申请号：US16879322

申请日：2020-05-20

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mirko Visontai ,  Christopher Walter George Thornton ,  Tara N. Sainath ,  Ehsan Variani ,  Izhak Shafran ,  Michiel A.u. Bacchiani

IPC: G10L15/16 ,  G10L15/02 ,  G10H1/00 ,  G10L19/02

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

公开(公告)号：US20190115013A1

公开(公告)日：2019-04-18

申请号：US16171629

申请日：2018-10-26

Applicant: Google LLC

Inventor： Samuel Bengio ,  Mirko Visontai ,  Christopher Walter George Thornton ,  Michiel A.U. Bacchiani ,  Tara N. Sainath ,  Ehsan Variani ,  Izhak Shafran

IPC: G10L15/16 ,  G10L19/02 ,  G10L15/02 ,  G10H1/00

CPC classification number: G10L15/16 ,  G10H1/00 ,  G10H2210/036 ,  G10H2210/046 ,  G10H2250/235 ,  G10H2250/311 ,  G10L15/02 ,  G10L17/18 ,  G10L19/0212

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.