Selection of speech units for a speaker-independent CSR task.
Lorenzo FissoreEgidio P. GiachinPietro LafaceGiorgio MiccaPublished in: EUROSPEECH (1991)
Keyphrases
- speaker independent
- speech recognition
- speaker dependent
- hidden markov models
- speaker identification
- speech recognizer
- digit recognition
- speaker adaptation
- speech recognition systems
- speech signal
- acoustic models
- speech synthesis
- automatic speech recognition
- emotion classification
- emotional speech
- emotion recognition
- spoken language
- vocal tract
- image processing
- noisy environments
- dialogue system
- audio visual
- gaussian mixture model
- language model
- pattern recognition
- similarity measure