A corpus-based approach to speech enhancement from nonstationary noise.
Ji MingRamji SrinivasanDanny CrookesPublished in: INTERSPEECH (2010)
Keyphrases
- non stationary
- speech enhancement
- speech signal
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- linear prediction
- background noise
- additive noise
- vocal tract
- autoregressive
- wiener filter
- random fields
- noisy speech
- automatic speech recognition
- multi channel
- speech recognition
- signal processing
- edge detection
- image structure
- motion estimation
- smoothing algorithm
- hidden markov models
- information retrieval