Speech Modelling Based on Acoustic-to-Articulatory Mapping.
Jean SchoentgenPublished in: Summer School on Neural Networks (2004)
Keyphrases
- acoustic features
- speech recognition
- vocal tract
- formant frequencies
- speech sounds
- speech signal
- speech recognition systems
- speech synthesis
- prosodic features
- automatic speech recognition
- speaker independent
- speech recognizers
- speaker verification
- acoustic models
- music information retrieval
- acoustic signal
- visual features
- multi stream
- vowel phonemes
- noisy speech
- hidden markov models
- speech recognizer
- speech enhancement
- language model
- data sets
- speaker identification
- noisy environments
- mel frequency cepstral coefficients
- broadcast news
- audio visual
- signal to noise ratio
- non stationary
- emotional speech
- multi modal
- multimedia