公开(公告)号：US09990918B1

公开(公告)日：2018-06-05

申请号：US15788300

申请日：2017-10-19

Applicant: Google Inc.

Inventor： William Chan ,  Navdeep Jaitly ,  Quoc V. Le ,  Oriol Vinyals ,  Noam M. Shazeer

IPC: G10L15/16 ,  G06F17/22 ,  G10L15/183 ,  G10L15/26

CPC classification number: G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

公开(公告)号：US09799327B1

公开(公告)日：2017-10-24

申请号：US15055476

申请日：2016-02-26

Applicant: Google Inc.

Inventor： William Chan ,  Navdeep Jaitly ,  Quoc V. Le ,  Oriol Vinyals ,  Noam M. Shazeer

IPC: G10L15/16 ,  G10L15/26 ,  G06F17/22 ,  G10L15/183

CPC classification number: G10L15/16

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing an utterance, and the input acoustic sequence comprising a respective acoustic feature representation at each of a first number of time steps; processing the input acoustic sequence using a first neural network to convert the input acoustic sequence into an alternative representation for the input acoustic sequence; processing the alternative representation for the input acoustic sequence using an attention-based Recurrent Neural Network (RNN) to generate, for each position in an output sequence order, a set of substring scores that includes a respective substring score for each substring in a set of substrings; and generating a sequence of substrings that represent a transcription of the utterance.

公开(公告)号：US20180150605A1

公开(公告)日：2018-05-31

申请号：US15362643

申请日：2016-11-28

Applicant: Google Inc.

Inventor： Christopher S. Co ,  Navdeep Jaitly ,  Lily Hao Yi Peng ,  Katherine Irene Chou ,  Ananth Sankar

IPC: G06F19/00 ,  G06F17/28 ,  G10L15/06 ,  G10L15/14 ,  G10L15/16 ,  G10L15/183

CPC classification number: G06F19/328 ,  G06F17/2836 ,  G06F17/289 ,  G10L15/063 ,  G10L15/142 ,  G10L15/16 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/26

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for speech recognition. One method includes obtaining an input acoustic sequence, the input acoustic sequence representing one or more utterances; processing the input acoustic sequence using a speech recognition model to generate a transcription of the input acoustic sequence, wherein the speech recognition model comprises a domain-specific language model; and providing the generated transcription of the input acoustic sequence as input to a domain-specific predictive model to generate structured text content that is derived from the transcription of the input acoustic sequence.

公开(公告)号：US20170140753A1

公开(公告)日：2017-05-18

申请号：US15349245

申请日：2016-11-11

Applicant: Google Inc.

Inventor： Navdeep Jaitly ,  Quoc V. Le ,  Oriol Vinyals ,  Samuel Bengio ,  Ilya Sutskever

IPC: G10L15/16 ,  G10L15/02 ,  G06F17/28

CPC classification number: G10L15/16 ,  G05B13/027 ,  G06F17/276 ,  G06F17/289 ,  G06N3/0445 ,  G10L15/02 ,  G10L15/26 ,  G10L2015/025

Abstract: A system can be configured to perform tasks such as converting recorded speech to a sequence of phonemes that represent the speech, converting an input sequence of graphemes into a target sequence of phonemes, translating an input sequence of words in one language into a corresponding sequence of words in another language, or predicting a target sequence of words that follow an input sequence of words in a language (e.g., a language model). In a speech recognizer, the RNN system may be used to convert speech to a target sequence of phonemes in real-time so that a transcription of the speech can be generated and presented to a user, even before the user has completed uttering the entire speech input.