Bayesian fusion of confidence measures for speech recognition

被引：8

作者：

Kim, TY ^{[1
]}

Ko, H ^{[1
]}

机构：

[1] Korea Univ, Dept Elect & Comp Engn, Seoul 136701, South Korea

来源：

IEEE SIGNAL PROCESSING LETTERS | 2005年 / 12卷 / 12期

关键词：

adaptive confidence scoring; Bayesian fusion; confidence measure (CM); speech recognition;

D O I：

10.1109/LSP.2005.859494

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The application of Bayesian fusion of confidence measures to speech recognition is proposed. Feature level, decision level, and hybrid fusion are considered under the Bayesian framework. The use of speaker-adapted feature-level Bayesian fusion reduced the error rate by 19.4% as compared to the conventional single feature-based confidence scoring in an isolated word out-of-vocabulary rejection test. The decision-level Bayesian fusion also showed better performance than the majority rule. Finally, hybrid Bayesian, fusion, which can combine both confidence measure features and local decisions, achieved the best performance.

引用

页码：871 / 874

页数：4

共 11 条

[1] Charlet D., 2001, P EUROSPEECH, P2113
[2] High-level approaches to confidence estimation in speech recognition
Cox, S
Dasmahapatra, S
[J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2002, 10 (07): : 460 - 471
[3] Gauvain J.-L., 1991, P DARPA SPEECH NAT L, P272
[4] Hall DL, 1997, P IEEE, V85, P6, DOI [10.1109/5.554205, 10.1109/ISCAS.1998.705329]
[5] KAMPPAR S, 2000, P ICASSP, V3, P5
[6] KIM T, 2003, P EUR GEN SWITZ, P889
[7] Kim TY, 2005, INT CONF ACOUST SPEE, P77
[8] MORENO PJ, 2001, P EUROSPEECH 01 AALB, P2109
[9] Sanchis A, 2003, 2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, P592
[10] Distributed detection with multiple sensors .1. Fundamentals
Viswanathan, R
Varshney, PK
[J]. PROCEEDINGS OF THE IEEE, 1997, 85 (01) : 54 - 63

← 1 2 →