Browse > Article

Bayesian Fusion of Confidence Measures for Confidence Scoring  

김태윤 (고려대학교 전자컴퓨터공학과)
고한석 (고려대학교 전자컴퓨터공학과)
Publication Information
The Journal of the Acoustical Society of Korea / v.23, no.5, 2004 , pp. 410-419 More about this Journal
Abstract
In this paper. we propose a method of confidence measure fusion under Bayesian framework for speech recognition. Centralized and distributed schemes are considered for confidence measure fusion. Centralized fusion is feature level fusion which combines the values of individual confidence scores and makes a final decision. In contrast. distributed fusion is decision level fusion which combines the individual decision makings made by each individual confidence measuring method. Optimal Bayesian fusion rules for centralized and distributed cases are presented. In isolated word Out-of-Vocabulary (OOV) rejection experiments. centralized Bayesian fusion shows over 13% relative equal error rate (EER) reduction compared with the individual confidence measure methods. In contrast. the distributed Bayesian fusion shows no significant performance increase.
Keywords
Speech recognition; Confidence measure; OOV nejection; Bayesian fusion; CM fusion;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Vocabulary Independent Discriminative Utterance Verification for Nonkeyword Rejection in Subword Based Speech Recognition /
[ Rafid A. Sukkar;Chin-Hui Lee ] / IEEE Trans. on Speech and Audio Processing   DOI   ScienceOn
2 Word Lavel Confidence Annotation using Combinations of Features /
[ Rong Zhang;Alexander Rudnicky ] / Proc. EUROSPEECH
3 Confidence Measures for Large Vocabulary Continuous Speech Recognition /
[ Frank Wessel;Schluter(et al.) ] / IEEE Trans. on Speech and Audio Processing   DOI   ScienceOn
4 Utterance Verification in Continuous Speech Recognition: Decoding and Training Procedures /
[ Eduardo Lleida;Richard C. Rose ] / IEEE Trans. on Speech and Audio Processing   DOI   ScienceOn
5 Word and Phone Level Acoustic Confidence Scoring /
[ Simo Kamppari;Timothy Hazen ] / proc. ICASSP
6 Neural-Network Based Measures of Confidence for Word Recognition /
[ Mitch Weintraub;Francoise Beaufays(et al.) ] / proc. ICASSP
7 A Boosting Approach for Confidence Scoring /
[ Pedro J. Moreno;Beth Logan(et al.) ] / proc. EUROSPEECH
8 An Introduction to Multisensor Data Fusion /
[ David L. Hall;James Llians ] / Proceedings of the IEEE   DOI   ScienceOn
9 Distributed Detection with Multiple Sensors: Part 1 - Fundamentals /
[ Ramanarayanan Viswanathan;Pramod Varshney ] / Proceedings of the IEEE   DOI   ScienceOn
10 /
[ Pramod Varshney ] / Distributed Detection and Data Fusion
11 An Algorithm for Datermining the Decision Thresholds in a Distributed Detection Problem /
[ Zhunag-Bo Tang;Krishna R. Pattipati(et al.) ] / IEEE Trans. on Sys., Man. and Cybernetics   DOI   ScienceOn
12 /
[ Fukunaga ] / Introduction to Statistical Pattern Recognition(2nd edition)
13 Is This Conversation on Track? /
[ Paul Carpenter;Chun Jin(et al.) ] / Proc. EUROSPEECH
14 Improved MLLR Speaker Adaptation Using Confidence Measures for Conversation Speech Recognition /
[ Micheal Pitz;Frank Wessel(et al.) ] / Proc. ICSLP