Recognising Speech in the Presence of a Competing Speaker using a 'Speech Fragment Decoder'.
André CoyJon BarkerPublished in: ICASSP (1) (2005)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker identification
- speech signal
- speech synthesis
- vocal tract
- speaker verification
- automatic speech recognition systems
- text to speech
- acoustic features
- automatic transcription
- speaker dependent
- prosodic features
- speaker diarization
- recognition engine
- acoustic models
- endpoint detection
- low complexity
- activity recognition
- speech recognizer
- linear prediction
- finite state transducers
- noisy environments
- dialogue system
- synthesized speech