Probabilistic acoustic tube: a probabilistic generative model of speech for speech analysis/synthesis.
Zhijian OuYang ZhangPublished in: AISTATS (2012)
Keyphrases
- speech recognition
- automatic speech recognition
- emotional speech
- recognition engine
- speech signal
- emotion recognition
- speaker recognition
- spoken language
- endpoint detection
- bayesian networks
- vocal tract
- speech synthesis
- speaker verification
- spectral analysis
- structural analysis
- audio visual
- statistical analysis
- data analysis
- natural language