-
公开(公告)号:US11580955B1
公开(公告)日:2023-02-14
申请号:US17218740
申请日:2021-03-31
Applicant: Amazon Technologies, Inc.
Inventor: Yixiong Meng , Roberto Barra Chicote , Grzegorz Beringer , Zeya Chen , Jie Liang , James Garnet Droppo , Chia-Hao Chang , Oguz Hasan Elibol
IPC: G10L13/08 , G10L13/027 , G10L15/06 , G10L13/033 , G10L19/008 , G10L13/047
Abstract: A speech-processing system receives input data representing text. A first encoder processes segments of the text to determine embedding data representing the text, and a second encoder processes corresponding audio data to determine prosodic data corresponding to the text. The embedding and prosodic data is processed to create output data including a representation of speech corresponding to the text and prosody.