Discriminatively estimated joint acoustic, duration, and language model for speech recognition.
Maider LehrIzhak ShafranPublished in: ICASSP (2010)
Keyphrases
- speech recognition
- language model
- speech recognition systems
- speaker independent
- speech recognizers
- language modeling
- acoustic models
- speech recognizer
- n gram
- probabilistic model
- document retrieval
- noisy speech
- retrieval model
- information retrieval
- automatic speech recognition
- speech signal
- speech synthesis
- query expansion
- mixture model
- word error rate
- speaker identification
- translation model
- test collection
- handwriting recognition
- noisy environments
- relevance model
- co occurrence
- query terms