公开(公告)号：US20230186907A1

公开(公告)日：2023-06-15

申请号：US18164923

申请日：2023-02-06

Applicant: Google LLC

Inventor： Ke Hu ,  Tara N. Sainath ,  Ruoming Pang ,  Rohit Prakash Prabhavalkar

IPC: G10L15/18 ,  G06N3/049 ,  G10L15/06 ,  G10L15/16 ,  G10L15/187 ,  G10L19/00

CPC classification number: G10L15/1815 ,  G06N3/049 ,  G10L15/063 ,  G10L15/16 ,  G10L15/187 ,  G10L19/0018

Abstract: A method of performing speech recognition using a two-pass deliberation architecture includes receiving a first-pass hypothesis and an encoded acoustic frame and encoding the first-pass hypothesis at a hypothesis encoder. The first-pass hypothesis is generated by a recurrent neural network (RNN) decoder model for the encoded acoustic frame. The method also includes generating, using a first attention mechanism attending to the encoded acoustic frame, a first context vector, and generating, using a second attention mechanism attending to the encoded first-pass hypothesis, a second context vector. The method also includes decoding the first context vector and the second context vector at a context vector decoder to form a second-pass hypothesis

公开(公告)号：US11908461B2

公开(公告)日：2024-02-20

申请号：US17149018

申请日：2021-01-14

Applicant: Google LLC

Inventor： Ke Hu ,  Tara N. Sainath ,  Ruoming Pang ,  Rohit Prakash Prabhavalkar

IPC: G10L15/18 ,  G06N3/049 ,  G10L15/06 ,  G10L15/16 ,  G10L15/187 ,  G10L19/00

CPC classification number: G10L15/1815 ,  G06N3/049 ,  G10L15/063 ,  G10L15/16 ,  G10L15/187 ,  G10L19/0018

Abstract: A method of performing speech recognition using a two-pass deliberation architecture includes receiving a first-pass hypothesis and an encoded acoustic frame and encoding the first-pass hypothesis at a hypothesis encoder. The first-pass hypothesis is generated by a recurrent neural network (RNN) decoder model for the encoded acoustic frame. The method also includes generating, using a first attention mechanism attending to the encoded acoustic frame, a first context vector, and generating, using a second attention mechanism attending to the encoded first-pass hypothesis, a second context vector. The method also includes decoding the first context vector and the second context vector at a context vector decoder to form a second-pass hypothesis.

公开(公告)号：US20220172706A1

公开(公告)日：2022-06-02

申请号：US17651315

申请日：2022-02-16

Applicant: Google LLC

Inventor： Ke Hu ,  Golan Pundak ,  Rohit Prakash Prabhavalkar ,  Antoine Jean Bruguier ,  Tara N. Sainath

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/187 ,  G10L15/193 ,  G10L15/28 ,  G10L15/32 ,  G10L25/30

Abstract: A method includes receiving audio data encoding an utterance spoken by a native speaker of a first language, and receiving a biasing term list including one or more terms in a second language different than the first language. The method also includes processing, using a speech recognition model, acoustic features derived from the audio data to generate speech recognition scores for both wordpieces and corresponding phoneme sequences in the first language. The method also includes rescoring the speech recognition scores for the phoneme sequences based on the one or more terms in the biasing term list, and executing, using the speech recognition scores for the wordpieces and the rescored speech recognition scores for the phoneme sequences, a decoding graph to generate a transcription for the utterance.

公开(公告)号：US20210225369A1

公开(公告)日：2021-07-22

申请号：US17149018

申请日：2021-01-14

Applicant: Google LLC

Inventor： Ke Hu ,  Tara N. Sainath ,  Ruoming Pang ,  Rohit Prakash Prabhavalkar

IPC: G10L15/18 ,  G10L15/06 ,  G06N3/04 ,  G10L15/187 ,  G10L15/16 ,  G10L19/00

Abstract: A method of performing speech recognition using a two-pass deliberation architecture includes receiving a first-pass hypothesis and an encoded acoustic frame and encoding the first-pass hypothesis at a hypothesis encoder. The first-pass hypothesis is generated by a recurrent neural network (RNN) decoder model for the encoded acoustic frame. The method also includes generating, using a first attention mechanism attending to the encoded acoustic frame, a first context vector, and generating, using a second attention mechanism attending to the encoded first-pass hypothesis, a second context vector. The method also includes decoding the first context vector and the second context vector at a context vector decoder to form a second-pass hypothesis