Enhancement of esophageal speech using formant synthesis.
Kenji MatsuiNoriyo HaraPublished in: ICASSP (1999)
Keyphrases
- speech signal
- speech recognition
- vocal tract
- automatic speech recognition
- automatic speech recognition systems
- linear prediction
- spectral analysis
- noisy environments
- speaker identification
- non stationary
- speech quality
- background noise
- hidden markov models
- image enhancement
- image processing
- speaker recognition
- program synthesis
- texture synthesis
- data sets
- fundamental frequency
- speech synthesis
- pattern recognition
- database
- language model
- face recognition
- speaker independent