Speech enhancement using a joint map estimator with Gaussian mixture model for (non-)stationary noise.
Balázs FodorTim FingscheidtPublished in: ICASSP (2011)
Keyphrases
- non stationary
- gaussian mixture model
- speech enhancement
- speech signal
- maximum a posteriori
- maximum likelihood
- noisy environments
- noise reduction
- speaker identification
- additive noise
- signal to noise ratio
- expectation maximization
- em algorithm
- mixture model
- speaker recognition
- background noise
- single channel
- vocal tract
- linear prediction
- automatic speech recognition
- wiener filter
- gaussian distribution
- autoregressive
- feature vectors
- speech recognition
- random fields
- background subtraction
- unsupervised learning
- hidden markov models
- feature extraction
- image processing
- image restoration