Acoustic To Articulatory Speech Inversion Using Multi-Resolution Spectro-Temporal Representations Of Speech Signals.
Rahil ParikhNadee SeneviratneGanesh SivaramanShihab ShammaCarol Y. Espy-WilsonPublished in: INTERSPEECH (2022)
Keyphrases
- speech signal
- acoustic features
- multiresolution
- vocal tract
- speech sounds
- speech recognition
- formant frequencies
- automatic speech recognition
- noisy speech
- sound source
- speaker identification
- automatic speech recognition systems
- speech recognition systems
- non stationary
- linear prediction
- speech enhancement
- vowel phonemes
- hidden markov models
- noisy environments
- mel frequency cepstral coefficients
- spectral subtraction
- speech synthesis
- background noise
- spectral analysis
- blind source separation
- speaker recognition
- speech quality
- wavelet transform
- audio signal
- computer vision
- text to speech
- image acquisition
- wavelet coefficients
- pattern recognition
- image processing