The Lincoln robust continuous speech recognizer
- 13 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The Lincoln stress-resistant HMM (hidden Markov model) CSR has been extended to large-vocabulary continuous speech for both speaker-dependent (SD) and speaker-independent (SI) tasks. Performance on the DARPA resource management task (991-word vocabulary, perplexity 60 word-pair grammar) is 3.5% word error rate for SD training of word-context-dependent triphone models and 12.6% word error rate for SI training of (word-context-free) tied-mixture triphone models.Keywords
This publication has 11 references indexed in Scilit:
- A speaker-stress resistant HMM isolated word recognizerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Multi-style training for robust isolated-word speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Two-stage discriminant analysis for improved isolated-word recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Context-dependent modeling for acoustic-phonetic recognition of continuous speechPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The DARPA 1000-word resource management database for continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Large-vocabulary speaker-independent continuous speech recognition using HMMPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Speaker stress-resistant continuous speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Continuous speech recognition results of the BYBLOS system on the DARPA 1000-word resource management databasePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A new algorithm for the estimation of hidden Markov model parametersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Cepstral domain talker stress compensation for robust speech recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1988