Current browse context:
eess.AS
Change to browse by:
References & Citations
Electrical Engineering and Systems Science > Audio and Speech Processing
Title: Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
(Submitted on 27 Mar 2024 (this version), latest version 1 May 2024 (v2))
Abstract: Transformers have been the most successful architecture for various speech modeling tasks, including speech separation. However, the self-attention mechanism in transformers with quadratic complexity is inefficient in computation and memory. Recent models incorporate new layers and modules along with transformers for better performance but also introduce extra model complexity. In this work, we replace transformers with Mamba, a selective state space model, for speech separation. We propose dual-path Mamba, which models short-term and long-term forward and backward dependency of speech signals using selective state spaces. Our experimental results on the WSJ0-2mix data show that our dual-path Mamba models match or outperform dual-path transformer models Sepformer with only 60% of its parameters, and the QDPN with only 30% of its parameters. Our large model also reaches a new state-of-the-art SI-SNRi of 24.4 dB.
Submission history
From: Xilin Jiang [view email][v1] Wed, 27 Mar 2024 05:00:08 GMT (235kb,D)
[v2] Wed, 1 May 2024 00:36:13 GMT (238kb,D)
Link back to: arXiv, form interface, contact.