A dynamic in-search discriminative training approach for large vocabulary speech recognition

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

Volumn 1, Issue , 2002, Pages

  Jiang, Hui ^a   Siohan, Olivier ^a   Soong, Frank K ^a   Lee, Chin Hui ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DISCRIMINATIVE TRAINING; HIDDEN MARKOV MODELS; SPEECH TRANSCRIPTION; VITERBI SEARCH PROCEDURE; VOCABULARY SPEECH RECOGNITION;

COMPUTATIONAL LINGUISTICS; DATABASE SYSTEMS; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES; MAXIMUM LIKELIHOOD ESTIMATION; NEURAL NETWORKS;

SPEECH RECOGNITION;

EID: 0036295824     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Maximum mutual information estimation of hidden Markov model parameters for speech recognition
2. Discriminant-function-based minimum recognition error rate pattern-recognition approach to speech recognition
3. High-performance connected digit recognition using maximum mutual information estimation
4. A data selection strategy for utterance verification in continuous speech recognition
5. Discriminative learning for minimum error training
6. Minimum classification error rate methods for speech recognition
7. Large scale discriminative training for speech recognition