Visio-articulatory to acoustic conversion of speech.
Michael PucherDietmar SchabusPublished in: AVSP (2015)
Keyphrases
- acoustic features
- speech recognition
- vocal tract
- speech sounds
- speech signal
- formant frequencies
- speech recognition systems
- speech synthesis
- speaker independent
- automatic speech recognition
- vowel phonemes
- noisy speech
- speech recognizers
- acoustic models
- speaker verification
- visual features
- speech recognizer
- multi stream
- prosodic features
- image acquisition
- speech enhancement
- audio features
- language model
- noisy environments
- music information retrieval
- pattern recognition
- non stationary
- source localization
- recognition engine
- sound source
- information retrieval
- linear prediction
- visual speech
- speaker diarization
- speaker identification
- business intelligence
- emotional speech
- audio stream
- speech segments
- underwater acoustic
- speaker recognition