Subspace based speech enhancement using Gaussian mixture model.
Achintya KunduSaikat ChatterjeeT. V. SreenivasPublished in: INTERSPEECH (2008)
Keyphrases
- gaussian mixture model
- speech enhancement
- noise reduction
- feature space
- noisy environments
- signal to noise ratio
- single channel
- speech signal
- mixture model
- feature vectors
- linear prediction
- maximum likelihood
- em algorithm
- background subtraction
- vocal tract
- principal component analysis
- speaker recognition
- speaker identification
- low dimensional
- dimensionality reduction
- smoothing algorithm
- wiener filter
- expectation maximization
- multi channel
- feature extraction
- denoising
- background noise
- high dimensional
- probabilistic model
- markov random field
- speech recognition
- gaussian distribution
- edge detection
- multiresolution
- similarity measure