Speech Enhancement Based on Non-stationary Noise-driven Geometric Spectral Subtraction and Phase Spectrum Compensation.
Md Tauhidul IslamUdoy SahaK. T. ShahidAhmed Bin HussainCelia ShahnazPublished in: CoRR (2018)
Keyphrases
- spectral subtraction
- non stationary
- speech signal
- speech enhancement
- noisy speech
- noisy environments
- speech recognition
- vocal tract
- background noise
- signal to noise ratio
- linear prediction
- automatic speech recognition
- additive noise
- noise reduction
- autoregressive
- single channel
- random fields
- pattern recognition
- noise removal
- edge preserving
- hidden markov models