Maximum Likelihood PSD Estimation for Speech Enhancement in Reverberation and Noise.
Adam KuklasinskiSimon DocloSøren Holdt JensenJesper JensenPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
- speech enhancement
- maximum likelihood
- additive noise
- noisy environments
- noise reduction
- signal to noise ratio
- parameter estimation
- single channel
- speech signal
- wiener filter
- background noise
- linear prediction
- vocal tract
- noise level
- em algorithm
- edge preserving
- noisy speech
- expectation maximization
- independent component analysis
- maximum a posteriori
- edge detection
- smoothing algorithm
- prediction error
- multi channel
- gaussian distribution
- automatic speech recognition
- spatial domain
- speech recognition
- pattern recognition
- feature extraction
- image processing