Noisy speech recognition by using output combination of discrete-mixture HMMs and continuous-mixture HMMs.
Tetsuo KosakaYou SaitoMasaharu KatoPublished in: INTERSPEECH (2009)
Keyphrases
- speech recognition
- hidden markov models
- noisy environments
- language model
- mixture model
- speech signal
- speech synthesis
- speech processing
- speech understanding
- pattern recognition
- automatic speech recognition
- speech recognizer
- handwriting recognition
- speech recognition technology
- keyword spotting
- speech recognition systems
- cepstral coefficients
- speech recognition errors
- speaker diarization
- noisy images
- speaker independent
- acoustic models
- speaker dependent
- speech retrieval
- speaker identification