专利检索 ap:("Google LLC") AND inv:"Chao-Han Huck Yang" 第 1 页

1.

发明公开
PARAMETER-EFFICIENT MODEL REPROGRAMMING FOR CROSS-LINGUAL SPEECH RECOGNITION 审中-公开

公开(公告)号：US20240185841A1

公开(公告)日：2024-06-06

申请号：US18490808

申请日：2023-10-20

申请人： Google LLC

发明人： Bo Li , Yu Zhang , Nanxin Chen , Rohit Prakash Prabhavalkar , Chao-Han Huck Yang , Tara N. Sainath , Trevor Strohman

IPC分类号： G10L15/065 , G10L15/00

CPC分类号： G10L15/065 , G10L15/005

摘要： A method includes obtaining an ASR model trained to recognize speech in a first language and receiving transcribed training utterances in a second language. The method also includes integrating the ASR model with an input reprogramming module and a latent reprogramming module. The method also includes adapting the ASR model to learn how to recognize speech in the second language by training the input reprogramming module and the latent reprogramming module while parameters of the ASR model are frozen.