Back to Search
Start Over
Dasformer: Deep Alternating Spectrogram Transformer For Multi/Single-Channel Speech Separation
- Source :
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
- Publication Year :
- 2023
- Publisher :
- IEEE, 2023.
-
Abstract
- For the task of speech separation, previous study usually treats multi-channel and single-channel scenarios as two research tracks with specialized solutions developed respectively. Instead, we propose a simple and unified architecture - DasFormer (Deep alternating spectrogram transFormer) to handle both of them in the challenging reverberant environments. Unlike frame-wise sequence modeling, each TF-bin in the spectrogram is assigned with an embedding encoding spectral and spatial information. With such input, DasFormer is then formed by multiple repetition of simple blocks each of which integrates 1) two multi-head self-attention (MHSA) modules alternately processing within each frequency bin & temporal frame of the spectrogram 2) MBConv before each MHSA for modeling local features on the spectrogram. Experiments show that DasFormer has a powerful ability to model the time-frequency representation, whose performance far exceeds the current SOTA models in multi-channel speech separation, and also achieves single-channel SOTA in the more challenging yet realistic reverberation scenario.<br />5 pages, accepted by ICASSP2023
- Subjects :
- FOS: Computer and information sciences
Sound (cs.SD)
Audio and Speech Processing (eess.AS)
FOS: Electrical engineering, electronic engineering, information engineering
Computer Science - Sound
Computer Science - Multimedia
Electrical Engineering and Systems Science - Audio and Speech Processing
Multimedia (cs.MM)
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- Accession number :
- edsair.doi.dedup.....96184894ee94a7873bcdc20bbeb9a750