A determination of the sensitivity of speech recognisers to speaker variability.
Trevor J. ThomasJeremy PeckhamEleftherios D. FrangoulisPublished in: ICASSP (1989)
Keyphrases
- speech recognition
- speaker recognition
- audio visual
- automatic speech recognition
- speaker verification
- speaker identification
- prosodic features
- vocal tract
- speaker dependent
- speech signal
- automatic speech recognition systems
- speaker diarization
- speech synthesis
- hidden markov models
- text to speech
- synthesized speech
- noisy environments
- gaussian mixture model
- speech sounds
- multi modal
- mel frequency cepstral coefficients
- sensitivity analysis
- acoustic features
- speech recognizer
- automatic transcription
- broadcast news
- audio stream
- audio signals
- recognition engine
- probabilistic neural network
- vector quantization
- pattern recognition
- speaker independent
- multi stream
- speaker adaptation
- neural network
- language model
- acoustic models
- high sensitivity
- phoneme recognition
- endpoint detection