Confidence scoring based on backward language models

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

Volumn 1, Issue , 2002, Pages

  Duchateau, Jacques ^a   Demuynck, Kris ^a   Wambacq, Patrick ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC SIGNAL PROCESSING; ALGORITHMS; CORRELATION METHODS; PATTERN RECOGNITION SYSTEMS; PROBABILITY; SPEECH ANALYSIS;

AUTOMATIC RECOGNITION SYSTEMS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION; N-GRAM LANGUAGE MODEL;

CONTINUOUS SPEECH RECOGNITION;

EID: 17444437850     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/icassp.2002.5743694     Document Type: Conference Paper

References (10)

1. Hypothesis dependent threshold setting for improved out-of-vocabulary data rejection
2. Use of word level side information to improve speech recognition
3. Contextual confidence measures for continuous speech recognition
4. Is this conversation on track?
5. Extracting, modelling and combining information in speech recognition
6. Evaluation of word confidence for speech recognition systems
7. Estimation of probabilities from sparse data for the language model component of a speech recognizer
8. Fast and accurate acoustic modelling with semi-continuous HMMs
9. HMM based acoustic modelling in large vocabulary speech recognition
10. An efficient search space representation for large vocabulary continuous speech recognition