Speech recognition using re-utterance recognition

Invention Grant

US07444286B2 Speech recognition using re-utterance recognition 有权

Title translation: 使用重新识别语音识别

Please log in to see more content

Patent Title: Speech recognition using re-utterance recognition
Patent Title (中): 使用重新识别语音识别
Application No.: US11005567

Application Date: 2004-12-05
Publication No.: US07444286B2

Publication Date: 2008-10-28
Inventor: Daniel L. Roth , Jordan R. Cohen
Applicant: Daniel L. Roth , Jordan R. Cohen
Agent Edward W. Porter
Main IPC: G10L11/00
IPC: G10L11/00

Speech recognition using re-utterance recognition

Abstract:

The present invention relates to speech recognition that enables a user to perform re-utterance recognition, in which speech recognition is performed upon both a second saying of a sequence of one or more words and upon an earlier saying of the same sequence to help the speech recognition better select one or more best scoring text sequences for the utterances.

Abstract(Chinese):

本发明涉及语音识别，其使得用户能够执行再话语识别，其中语音识别是在对一个或多个单词的序列的第二语言进行的，并且根据相同序列的较早说话来帮助语音识别更好地为话语选择一个或多个最佳得分文本序列。

Public/Granted literature

US20050159950A1 Speech recognition using re-utterance recognition Public/Granted day:2005-07-21

Information query

Espacenet