A comparison and combination of methods for OOV word detection and word confidence scoring

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2001, Pages 397-400

  Hazen, Timothy J ^a   Bazzi, Issam ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

GENERIC WORD MODEL; OUT OF VOCABULARY WORD; WORD CONFIDENCE SCORING;

COMPUTER APPLICATIONS; MATHEMATICAL MODELS; NUMERICAL METHODS; SPEECH ANALYSIS;

SPEECH RECOGNITION;

EID: 0034843061     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.940851     Document Type: Article

References (13)

1. Modeling out-of-vocabulary words for robust speech recognition
2. A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)
3. Real-time telephone-based speech recognition in the JUPITER domain
4. Heterogeneous measurements and multiple classifiers for speech recognition
5. Recognition confidence scoring for use in speech understanding systems
6. Integrating recognition confidence scoring with language understanding and dialogue modeling
7. Word and phone level acoustic confidence scoring
8. Combination and joint training of acoustic classifiers for speech recognition
9. Acoustical and lexical based confidence measures for a very large vocabulary telephone speech hypothesis-verification system
10. A segment-based spotter using phonetic filler models
11. A hidden Markov model based keyword recognition system
12. Advances in confidence measures for large vocabulary
13. Jupiter: A telephone-based conversational interface for weather information