A nonlinear articulatory speech synthesizer using both time- and frequency-domain elements.
Man Mohan SondhiJuergen SchroeterPublished in: ICASSP (1986)
Keyphrases
- frequency domain
- speech recognition
- speech synthesis
- text to speech
- vocal tract
- speech signal
- spatial domain
- fourier transform
- cross correlation
- multi stream
- power spectrum
- feature extraction
- denoising
- subband
- fourier analysis
- spectral domain
- filter bank
- automatic speech recognition
- discrete fourier transform
- speaker identification
- frequency analysis
- low pass
- noisy environments
- image compression
- frequency spectrum
- high quality
- facial asymmetry
- formant frequencies
- fourier domain
- audio visual
- language model
- hidden markov models
- phase correlation
- bandpass
- frequency response
- spectral analysis
- image coding
- multiresolution
- spectrum analysis
- computer vision
- machine learning