Fast Speaker Adaptation Using Multi-stream Based Eigenvoice in Noisy Environments.
Hwa Jeon SongHyung Soon KimPublished in: TSD (2006)
Keyphrases
- noisy environments
- speaker adaptation
- speech recognition
- multi stream
- hidden markov models
- audio visual speech recognition
- automatic speech recognition
- speech signal
- speaker verification
- speech recognizer
- speaker independent
- audio visual
- digit recognition
- speaker identification
- speech synthesis
- language model
- pattern recognition
- multi modal
- image processing
- maximum likelihood
- multimedia