公开(公告)号：US10762894B2

公开(公告)日：2020-09-01

申请号：US14805704

申请日：2015-07-22

Applicant: Google LLC

Inventor： Tara N. Sainath ,  Maria Carolina Parada San Martin

IPC: G10L15/16 ,  G06N3/04 ,  G10L15/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for keyword spotting. One of the methods includes training, by a keyword detection system, a convolutional neural network for keyword detection by providing a two-dimensional set of input values to the convolutional neural network, the input values including a first dimension in time and a second dimension in frequency, and performing convolutional multiplication on the two-dimensional set of input values for a filter using a frequency stride greater than one to generate a feature map.

公开(公告)号：US20200160836A1

公开(公告)日：2020-05-21

申请号：US16684483

申请日：2019-11-14

Applicant: GOOGLE LLC

Inventor： Zhifeng Chen ,  Bo Li ,  Eugene Weinstein ,  Yonghui Wu ,  Pedro J. Moreno Mengibar ,  Ron J. Weiss ,  Khe Chai Sim ,  Tara N. Sainath ,  Patrick An Phu Nguyen

IPC: G10L15/00 ,  G10L15/07 ,  G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable media, for speech recognition using multi-dialect and multilingual models. In some implementations, audio data indicating audio characteristics of an utterance is received. Input features determined based on the audio data are provided to a speech recognition model that has been trained to output score indicating the likelihood of linguistic units for each of multiple different language or dialects. The speech recognition model can be one that has been trained using cluster adaptive training. Output that the speech recognition model generated in response to receiving the input features determined based on the audio data is received. A transcription of the utterance generated based on the output of the speech recognition model is provided.

公开(公告)号：US20190259409A1

公开(公告)日：2019-08-22

申请号：US16278830

申请日：2019-02-19

Applicant: Google LLC

Inventor： Ehsan Variani ,  Kevin William Wilson ,  Ron J. Weiss ,  Tara N. Sainath ,  Arun Narayanan

IPC: G10L25/30 ,  G10L21/028 ,  G10L19/008 ,  G10L15/20 ,  G10L15/16 ,  G10L21/0388

Abstract: This specification describes computer-implemented methods and systems. One method includes receiving, by a neural network of a speech recognition system, first data representing a first raw audio signal and second data representing a second raw audio signal. The first raw audio signal and the second raw audio signal describe audio occurring at a same period of time. The method further includes generating, by a spatial filtering layer of the neural network, a spatial filtered output using the first data and the second data, and generating, by a spectral filtering layer of the neural network, a spectral filtered output using the spatial filtered output. Generating the spectral filtered output comprises processing frequency-domain data representing the spatial filtered output. The method still further includes processing, by one or more additional layers of the neural network, the spectral filtered output to predict sub-word units encoded in both the first raw audio signal and the second raw audio signal.

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.