Unsupervised acoustic model training

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

Volumn 1, Issue , 2002, Pages

  Lamel, Lori ^a   Gauvain, Jean Luc ^a   Adda, Gilles ^a  

^a CNRS   (France)

Author keywords

[No Author keywords available]

Indexed keywords

SPEECH RECOGNIZER; UNSUPERVISED TRAINING;

ACOUSTIC WAVES; LEARNING SYSTEMS; MATHEMATICAL MODELS; SPEECH PROCESSING;

SPEECH RECOGNITION;

EID: 0036296017     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Transcriber: Development and use of a tool for assisting speech corpora production
2. The TDT-2 text and speech corpus
3. Transcribing broadcast news: The LIMSI Nov96 Hub4 System
4. The LIMSI broadcast news transcription system
5. Fast decoding for indexation of broadcast data
6. Unsupervised training of a speech recognizer: Recent experiments
7. Lightly supervised acoustic model training
8. Investigating lightly supervised acoustic model training
9. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models
10. Broadcast news 1999 test results
11. Utilizing untranscribed training data to improve performance