公开(公告)号：US11955122B1

公开(公告)日：2024-04-09

申请号：US17487434

申请日：2021-09-28

Applicant: Amazon Technologies, Inc.

Inventor： Mansour Ahmadi ,  Udhgee Murugesan ,  Roger Hau-Bin Cheng ,  Roberto Barra Chicote ,  Kian Jamali Abianeh ,  Yixiong Meng ,  Oguz Hasan Elibol ,  Itay Teller ,  Kevin Kwanghoon Ha ,  Andrew Roths

IPC: G10L15/22 ,  G06N3/044 ,  G10L15/02 ,  G10L15/16 ,  G10L15/18 ,  G10L25/21 ,  G10L25/30 ,  G10L25/69 ,  G10L15/08

CPC classification number: G10L15/22 ,  G06N3/044 ,  G10L15/02 ,  G10L15/16 ,  G10L15/18 ,  G10L25/21 ,  G10L25/30 ,  G10L25/69 ,  G10L2015/088

Abstract: Techniques for determining whether audio is machine-outputted or non-machine-outputted are described. A device may receive audio, may process the audio to determine audio data including audio features corresponding to the audio, and may process the audio data to determine audio embedding data. The device may process the audio embedding data to determine whether the audio is machine-outputted or non-machine-outputted. In response to determining that the audio is machine-outputted, then the audio may be discarded or not processed further. Alternatively, in response to determining that the audio is non-machine-outputted (e.g., live speech from a user), then the audio may be processed further (e.g., using ASR processing).

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.