A Novel Risk-Estimation-Theoretic Framework for Speech Enhancement in Nonstationary and Non-Gaussian Noise Conditions.
Jishnu SadasivanChandra Sekhar SeelamantulaPublished in: INTERSPEECH (2016)
Keyphrases
- non stationary
- theoretic framework
- speech enhancement
- speech signal
- noisy environments
- noise reduction
- signal to noise ratio
- information theoretic
- linear prediction
- single channel
- autoregressive
- background noise
- additive noise
- vocal tract
- noisy speech
- blind source separation
- automatic speech recognition
- random fields
- wiener filter
- parameter estimation
- smoothing algorithm
- gaussian markov random fields
- edge preserving
- multi channel
- speech recognition
- image processing
- image quality
- signal processing
- mutual information