A comparative study of acoustic-to-articulatory inversion for neutral and whispered speech.
Aravind IllaNisha MeenakshiPrasanta Kumar GhoshPublished in: ICASSP (2017)
Keyphrases
- acoustic features
- speech recognition
- vocal tract
- endpoint detection
- speech sounds
- speech signal
- formant frequencies
- speech recognition systems
- speech synthesis
- automatic speech recognition
- speaker verification
- speaker independent
- speech recognizers
- prosodic features
- acoustic models
- noisy speech
- comparative study
- noisy environments
- speech recognizer
- vowel phonemes
- music information retrieval
- multi stream
- speaker identification
- speech enhancement
- visual features
- image reconstruction
- text to speech
- pattern recognition
- emotional speech
- sound source
- audio features
- mel frequency cepstral coefficients
- speaker recognition
- image acquisition
- acoustic signal
- language model
- laplace transform
- recognition engine
- speech segments
- source localization
- sensor networks
- feature vectors