Acoustic-to-articulatory inversion using speech recognition and trajectory formation based on phoneme hidden Markov models.
Atef Ben YoussefPierre BadinGérard BaillyPanikos HeracleousPublished in: INTERSPEECH (2009)
Keyphrases
- speech recognition
- hidden markov models
- speech recognition systems
- speaker independent
- speech recognizers
- acoustic models
- automatic speech recognition
- speech synthesis
- acoustic features
- speech recognizer
- speech signal
- noisy speech
- speaker dependent
- speech processing
- visual speech
- phoneme recognition
- speaker identification
- noisy environments
- vocal tract
- handwriting recognition
- conditional random fields
- visual speech recognition
- isolated word recognition
- speaker recognition
- keyword spotting
- mel frequency cepstral coefficients
- multi stream
- audio signal
- language model
- information extraction
- neural network