公开(公告)号：US09779724B2

公开(公告)日：2017-10-03

申请号：US14532208

申请日：2014-11-04

Applicant: Google Inc.

Inventor： Alexander H. Gruenstein ,  Dave Harwath ,  Ian C. McGraw

IPC: G10L15/00 ,  G10L15/08 ,  G10L15/04 ,  G10L15/22

CPC classification number: G10L15/08 ,  G10L2015/221

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting alternates in speech recognition. In some implementations, data is received that indicates multiple speech recognition hypotheses for an utterance. Based on the multiple speech recognition hypotheses, multiple alternates for a particular portion of a transcription of the utterance are identified. For each of the identified alternates, one or more features scores are determined, the features scores are input to a trained classifier, and an output is received from the classifier. A subset of the identified alternates is selected, based on the classifier outputs, to provide for display. Data indicating the selected subset of the alternates is provided for display.

公开(公告)号：US20180012592A1

公开(公告)日：2018-01-11

申请号：US15703033

申请日：2017-09-13

Applicant: Google Inc.

Inventor： Alexander H. Gruenstein ,  Dave Harwath ,  Ian C. McGraw

IPC: G10L15/08 ,  G10L15/22

CPC classification number: G10L15/08 ,  G10L2015/221

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting alternates in speech recognition. In some implementations, data is received that indicates multiple speech recognition hypotheses for an utterance. Based on the multiple speech recognition hypotheses, multiple alternates for a particular portion of a transcription of the utterance are identified. For each of the identified alternates, one or more features scores are determined, the features scores are input to a trained classifier, and an output is received from the classifier. A subset of the identified alternates is selected, based on the classifier outputs, to provide for display. Data indicating the selected subset of the alternates is provided for display.

公开(公告)号：US20170220925A1

公开(公告)日：2017-08-03

申请号：US15394617

申请日：2016-12-29

Applicant: Google Inc.

Inventor： Ouais Alsharif ,  Rohit Prakash Prabhavalkar ,  Ian C. McGraw ,  Antoine Jean Bruguier

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/0445 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a compressed recurrent neural network (RNN). One of the systems includes a compressed RNN, the compressed RNN comprising a plurality of recurrent layers, wherein each of the recurrent layers has a respective recurrent weight matrix and a respective inter-layer weight matrix, and wherein at least one of recurrent layers is compressed such that a respective recurrent weight matrix of the compressed layer is defined by a first compressed weight matrix and a projection matrix and a respective inter-layer weight matrix of the compressed layer is defined by a second compressed weight matrix and the projection matrix.

公开(公告)号：US20150127346A1

公开(公告)日：2015-05-07

申请号：US14532208

申请日：2014-11-04

Applicant: Google Inc.

Inventor： Alexander H. Gruenstein ,  Dave Harwath ,  Ian C. McGraw

IPC: G10L15/08

CPC classification number: G10L15/08 ,  G10L2015/221

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting alternates in speech recognition. In some implementations, data is received that indicates multiple speech recognition hypotheses for an utterance. Based on the multiple speech recognition hypotheses, multiple alternates for a particular portion of a transcription of the utterance are identified. For each of the identified alternates, one or more features scores are determined, the features scores are input to a trained classifier, and an output is received from the classifier. A subset of the identified alternates is selected, based on the classifier outputs, to provide for display. Data indicating the selected subset of the alternates is provided for display.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于选择语音识别中的替代。 在一些实现中，接收到指示用于话语的多个语音识别假设的数据。 基于多个语音识别假设，识别出话音转录的特定部分的多个替代。 对于每个识别的替代物，确定一个或多个特征得分，将特征得分输入到经过训练的分类器，并从分类器接收输出。 基于分类器输出来选择所识别的替代物的子集，以提供显示。 指示所选择的替代子集的数据被提供用于显示。