Speech recognition using syllable-like units.
Zhihong HuJohan SchalkwykEtienne BarnardRonald A. ColePublished in: ICSLP (1996)
Keyphrases
- prosodic features
- synthesized speech
- speech recognition
- speech synthesis
- text to speech
- n gram
- automatic speech recognition
- speech signal
- recognition engine
- language acquisition
- audio visual
- video sequences
- vocal tract
- emotion recognition
- spoken language
- speaker identification
- human communication
- endpoint detection
- text to speech synthesis
- multi lingual
- speaker recognition
- speaker verification
- spoken dialogue systems
- dialogue system
- gaussian mixture model