On including temporal constraints in Viterbi alignment for speech recognition in noise.
Néstor Becerra YomaFergus R. McInnesMervyn A. JackSandra Dotto StumpLee Luan LingPublished in: IEEE Trans. Speech Audio Process. (2001)
Keyphrases
- speech recognition
- temporal constraints
- hidden markov models
- noisy environments
- temporal reasoning
- noisy speech
- simple temporal
- automatic speech recognition
- language model
- speech signal
- speech processing
- speaker identification
- temporal information
- speech recognition systems
- speech synthesis
- pattern recognition
- speech recognizer
- speech recognition technology
- background noise
- speaker independent
- image processing
- speech recognizers
- noise reduction
- noise model
- signal to noise ratio
- constraint satisfaction problems
- functional dependencies
- speaker adaptation
- low level
- search algorithm