Visio-articulatory to acoustic conversion of speech.
Michael PucherDietmar SchabusPublished in: FAA (2015)
Keyphrases
- acoustic features
- vocal tract
- speech recognition
- speech sounds
- speech signal
- formant frequencies
- speech recognition systems
- automatic speech recognition
- speech synthesis
- speaker independent
- noisy speech
- speaker verification
- acoustic models
- speech recognizers
- vowel phonemes
- visual features
- prosodic features
- multi stream
- speech recognizer
- mel frequency cepstral coefficients
- music information retrieval
- sound source
- speaker identification
- language model
- image acquisition
- speech enhancement
- speaker recognition
- audio stream
- noisy environments
- text to speech
- broadcast news
- emotional speech
- underwater acoustic
- source localization
- linear prediction
- non stationary
- management system