Title:
センサ・ベース音声認識装置の選択、適応、および組合せ
Document Type and Number:
Japanese Patent JP2006510933
Kind Code:
A
Abstract:
A method and respective system for operating a speech recognition system, in which a plurality of recognizer programs are accessible to be activated for speech recognition, and are combined on a per need basis in order to efficiently improve the results of speech recognition done by a single recognizer. In order to adapt such system to the dynamically changing acoustic conditions of various operating environments and to the particular requirements of running in embedded systems having only a limited computing power available, it is proposed to a) collect selection base data characterizing speech recognition boundary conditions, e.g. the speaker person and the environmental noise, etc., with sensor means, and b) using program-controlled arbiter means for evaluating the collected data, e.g., a decision engine including software mechanism and a physical sensor, to select the best suited recognizer or a combination thereof out of the plurality of available recognizers.
Inventors:
Fisher, Volker
Kansman, Siegfried
Kansman, Siegfried
Application Number:
JP2004561151A
Publication Date:
March 30, 2006
Filing Date:
October 31, 2003
Export Citation:
Assignee:
INTERNATIONAL BUSINESS MASCHINES CORPORATION
International Classes:
G10L15/32; G10L15/00; G10L15/06; G10L15/065; G10L15/08; G10L15/14; G10L15/20; G10L15/26; G10L15/22
Domestic Patent References:
| JP2001517816A | 2001-10-09 | |||
| JP2000075889A | 2000-03-14 | |||
| JPH0573088A | 1993-03-26 | |||
| JP2002123278A | 2002-04-26 | |||
| JPH1011085A | 1998-01-16 | |||
| JP2002358093A | 2002-12-13 | |||
| JP2000276188A | 2000-10-06 | |||
| JPS5730913A | 1982-02-19 | |||
| JPH0683387A | 1994-03-25 |
Foreign References:
| US5960397A | 1999-09-28 |
Attorney, Agent or Firm:
Hiroshi Sakaguchi
Yoshihiro City
Takeshi Ueno
Yoshihiro City
Takeshi Ueno