STFT phase reconstruction in voiced speech for an improved single-channel speech enhancement.
Martin KrawczykTimo GerkmannPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2014)
Keyphrases
- speech enhancement
- single channel
- speech signal
- frequency domain
- multi channel
- vocal tract
- speech recognition
- noisy environments
- automatic speech recognition
- linear prediction
- noise reduction
- brain activity
- signal to noise ratio
- independent component analysis
- prior information
- wavelet decomposition
- wiener filter
- background noise
- non stationary
- pattern recognition
- sound source
- image segmentation
- additive noise
- multi frame
- computational complexity
- subband
- hidden markov models