Speech Conv-Mamba: Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation
IEEE Signal Processing Letters · 2025 · 32 · 2015-2019
DOI: 10.1109/lsp.2025.3560237 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2025. Verfasst von Debang Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Chongqing.
Abstract (Originalsprache)
As a selective state space model, Mamba exhibits outstanding performance and efficiency in sequence modeling tasks. Therefore, in this letter, we use Mamba as the fundamental network component to construct a novel speech separation model, Speech Conv-Mamba. Specifically, this model embeds Mamba within a U-shaped convolutional network to build the encoder and decoder network for high-dimensional representation and waveform reconstruction of speech signals. Additionally, we stack multiple temporal dilated convolutions and Mamba to create the separation network for separation task. Our comparative experiments on the GRID2Mix and Libri2Mix datasets demonstrate that the proposed model Speech Conv-Mamba, which achieves 98% and 89% of SepFormer's separation accuracy on two datasets using only 9% (2.4 M) of its model size, provides much less computational complexity and training cost.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Chongqing
Zitieren
APA
Liu, D., Zhang, T., Wei, Y., Yi, C., & Christensen, M. G. (2025). Speech Conv-Mamba: Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation. IEEE Signal Processing Letters, 32, 2015-2019. https://doi.org/10.1109/lsp.2025.3560237
Vancouver
Liu D, Zhang T, Wei Y, Yi C, Christensen MG. Speech Conv-Mamba: Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation. IEEE Signal Processing Letters. 2025;32:2015-2019. doi:10.1109/lsp.2025.3560237
BibTeX
@article{Liu2025,
author = {Liu, Debang and Zhang, Tianqi and Wei, Ying and Yi, Chen and Christensen, Mads Græsbøll},
title = {Speech Conv-Mamba: Selective Structured State Space Model With Temporal Dilated Convolution for Efficient Speech Separation},
journal = {IEEE Signal Processing Letters},
year = {2025},
volume = {32},
pages = {2015--2019},
doi = {10.1109/lsp.2025.3560237}
}
EUVIMED