A gain factor adapted by masking property and SNR variation for speech enhancement in colored-noise corruptions.
Ching-Ta LuKun-Fu TsengPublished in: Comput. Speech Lang. (2010)
Keyphrases
- speech enhancement
- signal to noise ratio
- noise reduction
- noisy environments
- single channel
- speech signal
- noisy speech
- linear prediction
- wiener filter
- background noise
- vocal tract
- multi channel
- additive noise
- edge preserving
- edge detection
- automatic speech recognition
- speech recognition
- frequency domain
- image restoration