Sub-convolutional U-Net with transformer attention network for end-to-end single-channel speech enhancement.
Sivaramakrishna YechuriSunny Dayal VanambathinaPublished in: EURASIP J. Audio Speech Music. Process. (2024)
Keyphrases
- end to end
- single channel
- speech enhancement
- multi channel
- noisy environments
- noise reduction
- signal to noise ratio
- frequency domain
- wavelet decomposition
- wiener filter
- independent component analysis
- background noise
- speech signal
- prior information
- brain activity
- vocal tract
- multiresolution
- sound source
- denoising
- spatial domain
- image coding
- high frequency
- multiscale