Error corrective mechanisms for speech recognition

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

Volumn 1, Issue , 2001, Pages 29-32

  Mangu, L ^a   Padmanabhan, M ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNIZER; WORD ERROR RATE;

CODING ERRORS; DECODING; MATHEMATICAL TRANSFORMATIONS; OPTIMIZATION; PATTERN RECOGNITION SYSTEMS; PROBABILITY; SPEECH CODING;

SPEECH RECOGNITION;

EID: 0034843104     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Transformation-based error-driven learning and natural language: A case study in part of speech tagging
2. Accurate methods for the statistics of surprise and coincidence
3. Transcription of broadcast news with a time constraint: IBM's 10xRT HUB4 system
4. Minimum bayes-risk automatic speech recognition
5. A winnow-based approach to context-sensitive spelling correction
6. The CU-HTK March 2000 Hub5e transcription workshop
7. Recent improvements in speech recognition performance on large conversational speech
8. Finding consensus in speech recognition: Word error minimization and other applications of confusion networks
9. Automatic rule acquisition for spelling correction
10. Maximum likelihood discriminant feature spaces
11. Explicit word error minimization in n-best list rescoring