Acoustic-to-articulatory inversion in speech based on statistical models.
Atef Ben YoussefPierre BadinGérard BaillyPublished in: AVSP (2010)
Keyphrases
- statistical models
- acoustic features
- speech recognition
- vocal tract
- formant frequencies
- speech sounds
- speech signal
- speech recognition systems
- statistical model
- automatic speech recognition
- speech synthesis
- statistical modeling
- speaker verification
- speaker independent
- acoustic models
- visual features
- prosodic features
- vowel phonemes
- parameter estimation
- speech recognizer
- multi stream
- music information retrieval
- hidden markov models
- audio features
- exponential family
- text to speech
- probability models
- audio stream
- visual speech
- sound source
- noisy environments
- audio visual
- bayesian models
- speaker recognition
- computer vision
- acoustic signal
- statistical methods
- language model
- relational databases