Automatic generation and selection of multiple pronunciations for dynamic vocabularies

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

Volumn 1, Issue , 2001, Pages 565-568

  Deligne, S ^a   Maison, B ^a   Gopinath, R ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC GENERATION; DYNAMIC VOCABULARIES; MULTIPLE PRONUNCIATIONS;

ACOUSTICS; SPEECH ANALYSIS; SPEECH RECOGNITION; WORD PROCESSING;

VOCABULARY CONTROL;

EID: 0034849094     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Automatic phonetic baseform determination
2. A user-configurable system for voice label recognition
3. Speech recognition using automatically derived baseforms
4. Phonological rules for enhancing acoustic enrollment of unknown words
5. Acoustics-only based automatic phonetic baseform generation
6. Acoustics-based baseform generation with pronunciation and/or phonotactic models
7. Modeling pronunciation variation for ASR: A survey of the literature
8. Dynamic pronunciation models for automatic speech recognition
9. Performance of the IBM large vocabulary continuous speech recognition system on the ARPA wall street journal task
10. Theory and practice of acoustic confusability