The sensitivity of speech recognisers to speaker variability and speaker variation.
Trevor ThomasJeremy PeckhamEleftherios D. FrangoulisJ. CovePublished in: EUROSPEECH (1989)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- speaker verification
- automatic speech recognition
- speaker identification
- speaker dependent
- speaker diarization
- prosodic features
- vocal tract
- automatic speech recognition systems
- synthesized speech
- acoustic features
- speech synthesis
- speech signal
- automatic transcription
- speaker independent
- hidden markov models
- speech sounds
- phoneme recognition
- acoustic models
- broadcast news
- speaker adaptation
- multi modal
- pattern recognition
- shape variations
- spontaneous speech
- intra personal
- recognition engine
- visual features
- model selection
- sensitivity analysis
- noisy environments
- maximum likelihood