公开(公告)号：US20250095634A1

公开(公告)日：2025-03-20

申请号：US18965193

申请日：2024-12-02

Applicant: Google LLC

Inventor： Bo Li ,  Tara N. Sainath ,  Ruoming Pang ,  Shuo-yiin Chang ,  Qiumin Xu ,  Trevor Strohman ,  Vince Chen ,  Qiao Liang ,  Heguang Liu ,  Yanzhang He ,  Parisa Haghani ,  Sameer Bidichandani

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/22 ,  G10L15/30

Abstract: A method includes receiving a sequence of acoustic frames characterizing one or more utterances as input to a multilingual automated speech recognition (ASR) model. The method also includes generating a higher order feature representation for a corresponding acoustic frame. The method also includes generating a hidden representation based on a sequence of non-blank symbols output by a final softmax layer. The method also includes generating a probability distribution over possible speech recognition hypotheses based on the hidden representation generated by the prediction network at each of the plurality of output steps and the higher order feature representation generated by the encoder at each of the plurality of output steps. The method also includes predicting an end of utterance (EOU) token at an end of each utterance. The method also includes classifying each acoustic frame as either speech, initial silence, intermediate silence, or final silence.

公开(公告)号：US12183322B2

公开(公告)日：2024-12-31

申请号：US17934555

申请日：2022-09-22

Applicant: Google LLC

Inventor： Bo Li ,  Tara N. Sainath ,  Ruoming Pang ,  Shuo-yiin Chang ,  Qiumin Xu ,  Trevor Strohman ,  Vince Chen ,  Qiao Liang ,  Heguang Liu ,  Yanzhang He ,  Parisa Haghani ,  Sameer Bidichandani

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/22 ,  G10L15/30

Abstract: A method includes receiving a sequence of acoustic frames characterizing one or more utterances as input to a multilingual automated speech recognition (ASR) model. The method also includes generating a higher order feature representation for a corresponding acoustic frame. The method also includes generating a hidden representation based on a sequence of non-blank symbols output by a final softmax layer. The method also includes generating a probability distribution over possible speech recognition hypotheses based on the hidden representation generated by the prediction network at each of the plurality of output steps and the higher order feature representation generated by the encoder at each of the plurality of output steps. The method also includes predicting an end of utterance (EOU) token at an end of each utterance. The method also includes classifying each acoustic frame as either speech, initial silence, intermediate silence, or final silence.