Explicit word error minimization using word hypothesis posterior probabilities

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

Volumn 1, Issue , 2001, Pages 33-36

  Wessel, F ^a   Schluter R ^a   Ney, H ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

BAYES DECISION RULE; SENTENCE ERROR RATE; TIME FRAME ERROR RATE; WORD ERROR RATE;

APPROXIMATION THEORY; CODING ERRORS; DECISION THEORY; DYNAMIC PROGRAMMING; MATHEMATICAL MODELS; PATTERN RECOGNITION SYSTEMS; PROBABILITY; RANDOM PROCESSES; SPEECH CODING;

SPEECH RECOGNITION;

EID: 0034856258     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. VERBMOBIL: The evolution of a complex large speech-to-speech translation system
2. Minimum bayes risc automatic speech recognition
3. Finding consensus among words: Lattice-based word error minimization
4. An overview of EU programs related to conversational/interactive systems
5. A word graph algorithm for large vocabulary continuous speech recognition
6. Explicit word error rate minimization in N-best list rescoring
7. LVCSR log-likelihood ratio scoring for keyword spotting
8. Using word probabilities as confidence measures
9. A comparison of word graph and N-best list based confidence measures
10. Using posterior probabilities for improved speech recognition
11. Confidence measures for large vocabulary continuous speech recognition