Acoustic modeling with contextual additive structure for HMM-based speech recognition.
Yoshihiko NankakuKazuhiro NakamuraHeiga ZenKeiichi TokudaPublished in: ICASSP (2008)
Keyphrases
- speech recognition
- hidden markov models
- speech recognition systems
- speaker independent
- automatic speech recognition
- speech recognizers
- speech recognizer
- speech processing
- speech synthesis
- language model
- speech understanding
- speech recognition technology
- acoustic models
- speech signal
- pattern recognition
- noisy speech
- speech retrieval
- speaker identification
- speaker dependent
- speech recognition errors
- computer vision
- cepstral coefficients