Waveform quantization of speech using Gaussian mixture models.
Jonas SamuelssonPublished in: ICASSP (1) (2004)
Keyphrases
- fundamental frequency
- speech recognition
- automatic speech recognition
- text to speech
- speaker identification
- speech synthesis
- language acquisition
- speech signal
- frequency domain
- recognition engine
- image formation
- quantization error
- audio visual
- broadcast news
- data sets
- hearing impaired
- vocal tract
- multi stream
- linear prediction
- frequency band
- computational complexity
- multiscale
- multimedia