Speech recognition with feeback from natural language processing for adaptation of acoustic model

• US 20050149318A1
• Filed: 03/08/2005
• Published: 07/07/2005
• Est. Priority Date: 09/30/1999
• Status: Active Grant

• Current Assignee: Hiroaki Ogawa, Hitoshj Honda, Hongchang Pao, Masanori Omote
• Original Assignee: Hiroaki Ogawa, Hitoshj Honda, Hongchang Pao, Masanori Omote
• Inventors: Omote, Masanori, Ogawa, Hiroaki, Honda, Hitoshj, Pao, Hongchang
• Granted Patent: US 7,158,934 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/075 supervised, i.e. under machine guidance
• CPC Class Codes: G10L 2015/0638 Interactive procedures

Abstract

A speech processing system including a speech recognition unit to receive input speech, and a natural language processor. The speech recognition unit performs speech recognition on input speech using acoustic models to produce a speech recognition result. The natural-language processor performs natural language processing on speech recognition result, and includes: a speech zone detector configured to detect correct zones from the speech recognition result; a feedback unit to feed back information obtained as a result of the natural language processing performed on the speech recognition result to said speech recognition unit. The feedback information includes the detected correct zones. The speech recognition unit includes an adaptation processor to process the feedback information to adapt the acoustic models so that the speech recognition unit produces the speech recognition result with higher precision than when the adaptation processor is not used.

Claims

1. A speech processing system comprising:

a speech recognition unit configured to receive and perform speech recognition on input speech to produce a speech recognition result using acoustic models; and

a natural-language processor configured to perform natural language processing on said speech recognition result, said natural-language processor including;

a speech zone detector configured to detect correct zones from said speech recognition result;

a feedback unit configured to feed back information obtained as a result of the natural language processing performed on said speech recognition result to said speech recognition unit, the feedback information including said detected correct zones,

wherein said speech recognition unit includes

an adaptation processor to process the feedback information from said feedback unit to adapt said acoustic models so that said speech recognition unit produces the speech recognition result with higher precision than when said adaptation processor is not used.