基本信息:
- 专利标题： Signal bias removal for robust telephone speech recognition
- 专利标题（中）：鲁棒语音识别在电话信号失真的校正。
- 申请号：EP95301747.2 申请日：1995-03-16
- 公开(公告)号：EP0674306A3 公开(公告)日：1997-09-10
- 发明人： Juang, Biing-Hwang , Rahim, Mazin G.
- 申请人： AT&T Corp.
- 申请人地址： 32 Avenue of the Americas New York, NY 10013-2412 US
- 专利权人： AT&T Corp.
- 当前专利权人： AT&T Corp.
- 当前专利权人地址： 32 Avenue of the Americas New York, NY 10013-2412 US
- 代理机构： Johnston, Kenneth Graham
- 优先权： US217035 19940324
- 主分类号： G10L3/00
- IPC分类号： G10L3/00
摘要：
A signal bias removal (SBR) method based on the maximum likelihood estimation of the bias for minimizing undesirable effects in speech recognition systems is described. The technique is readily applicable in various architectures including discrete (vector-quantization based), semicontinuous and continuous-density Hidden Markov Model (HMM) systems. For example, the SBR method can be integrated into a discrete density HMM and applied to telephone speech recognition where the contamination due to extraneous signal components is unknown. To enable real-time implementation, a sequential method for the estimation of the bias (SSBR) is disclosed.
公开/授权文献:
- EP0674306A2 Signal bias removal for robust telephone speech recognition 公开/授权日：1995-09-27