Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models.
Hironori DoiKeigo NakamuraTomoki TodaHiroshi SaruwatariKiyohiro ShikanoPublished in: IEICE Trans. Inf. Syst. (2010)
Keyphrases
- gaussian mixture model
- speech signal
- speech enhancement
- mel frequency cepstral coefficients
- speaker recognition
- speaker identification
- speech recognition
- mixture model
- noisy environments
- vocal tract
- automatic speech recognition
- background noise
- additive noise
- maximum likelihood criterion
- expectation maximization
- signal to noise ratio
- noise reduction
- hidden markov models
- em algorithm
- linear prediction
- acoustic features
- maximum likelihood
- spectral analysis
- single channel
- non stationary
- signal processing
- feature vectors
- feature space
- feature extraction
- face recognition
- similarity measure
- object recognition
- smoothing algorithm
- generative model
- probability density function