Speech Enhancement in Adverse Environments Based on Non-stationary Noise-driven Spectral Subtraction and SNR-dependent Phase Compensation.
Md Tauhidul Islam AsaduzzamanCelia ShahnazWei-Ping ZhuM. Omair AhmadPublished in: CoRR (2018)
Keyphrases
- non stationary
- speech enhancement
- spectral subtraction
- speech signal
- signal to noise ratio
- noisy environments
- noise reduction
- linear prediction
- vocal tract
- noisy speech
- single channel
- automatic speech recognition
- background noise
- additive noise
- autoregressive
- wiener filter
- speech recognition
- random fields
- noise level
- multi channel
- image denoising
- information retrieval