Acoustic-articulatory evaluation of the upper vowel-formant region and its presumed speaker-specific potency.
Frantz ClermontParham MokhtariPublished in: ICSLP (1998)
Keyphrases
- probabilistic model
- vocal tract
- speech recognition
- speech signal
- speaker independent
- speech synthesis
- speech recognition systems
- speech sounds
- prosodic features
- acoustic features
- vowel phonemes
- formant frequencies
- automatic speech recognition
- speaker identification
- image acquisition
- mel frequency cepstral coefficients
- hidden markov models
- acoustic models
- text to speech
- speaker verification
- domain specific
- speaker recognition
- data sets
- noisy environments
- evaluation method
- high level
- speech recognizer
- non stationary
- input image