Speech enhancement combining statistical models and NMF with update of speech and noise bases.
Kisoo KwonJong Won ShinSukanya SonowalIn Kyu ChoiNam Soo KimPublished in: ICASSP (2014)
Keyphrases
- speech enhancement
- statistical models
- noisy environments
- noise reduction
- signal to noise ratio
- speech signal
- statistical model
- noisy speech
- single channel
- statistical modeling
- linear prediction
- vocal tract
- speech recognition
- background noise
- spectral subtraction
- parameter estimation
- additive noise
- multi channel
- edge detection
- smoothing algorithm
- wiener filter
- automatic speech recognition
- edge preserving
- hidden markov models
- independent component analysis
- feature extraction
- prediction error
- image acquisition
- noisy images