A Regression Approach to Single-Channel Speech Separation Via High-Resolution Deep Neural Networks.
Jun DuYanhui TuLi-Rong DaiChin-Hui LeePublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2016)
Keyphrases
- single channel
- speech enhancement
- neural network
- high resolution
- multi channel
- sound source
- speech signal
- independent component analysis
- audio visual
- wiener filter
- signal to noise ratio
- speech recognition
- regression model
- pattern recognition
- frequency domain
- high frequency
- wavelet decomposition
- image processing
- noise reduction
- super resolution
- prior information
- remote sensing
- signal processing
- noisy environments
- regression analysis
- linear prediction
- high quality
- model selection
- brain activity
- vocal tract
- hidden markov models
- markov random field
- additive noise
- spatial resolution
- optical flow
- speech synthesis
- sar images