A Two-Channel Noise Estimator for Speech Enhancement in a Highly Nonstationary Environment.
Min-Seok ChoiHong-Goo KangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2011)
Keyphrases
- non stationary
- speech enhancement
- noisy environments
- speech signal
- single channel
- noise reduction
- multi channel
- signal to noise ratio
- background noise
- linear prediction
- additive noise
- random fields
- least squares
- automatic speech recognition
- autoregressive
- speech recognition
- adaptive filtering
- vocal tract
- noisy speech
- wavelet decomposition
- prior information
- frequency domain
- maximum likelihood
- wiener filter
- edge detection
- multiscale