Utterance-level boosting of HMM speech recognizers

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

Volumn 1, Issue , 2002, Pages

  Meyer, Carsten ^a  

^a PHILIPS RESEARCH LABORATORIES   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; MARKOV PROCESSES; MAXIMUM LIKELIHOOD ESTIMATION; NEURAL NETWORKS; PROBABILITY DISTRIBUTIONS; WORD PROCESSING;

ADABOOST ALGORITHM; BASELINE MODEL; HIDDEN MARKOV MODELS; MAXIMUM LIKELIHOOD TRAINING; UTTERANCE LEVEL BOOSTING;

SPEECH RECOGNITION;

EID: 0036293851     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/icassp.2002.5743666     Document Type: Conference Paper

References (9)

1. The strength of weak learnability
2. Discriminative model combination
3. A decision-theoretic generalization of on-line learning and an application to boosting
4. Theoretical views of boosting and applications
5. Boosting the margin: A new explanation of the effectiveness of voting methods
6. Boosting the performance of connectionist large vocabulary speech recognition
7. Using boosting to improve a hybrid HMM/neural network speech recognizer
8. Boosting Gaussian mixtures in an LVCSR system
9. Obtaining confidence measures from sentence probabilities