Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915386465714176 |
|---|---|
| author | Gao, Wenmiao Yin, Han |
| author_facet | Gao, Wenmiao Yin, Han |
| contents | Pre-training methods have greatly improved the performance of sound event localization and detection (SELD). However, existing Transformer-based models still face high computational cost. To solve this problem, we present a stereo SELD system using a pre-trained PSELDnet and a bidirectional Mamba sequence model. Specifically, we replace the Conformer module with a BiMamba module. We also use asymmetric convolutions to better capture the time and frequency relationships in the audio signal. Test results on the DCASE2025 Task 3 development dataset show that our method performs better than both the baseline and the original PSELDnet with a Conformer decoder. In addition, the proposed model costs fewer computing resources than the baselines. These results show that the BiMamba architecture is effective for solving key challenges in SELD tasks. The source code is publicly accessible at https://github.com/ alexandergwm/DCASE2025 TASK3 Stereo PSELD Mamba. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09570 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet Gao, Wenmiao Yin, Han Audio and Speech Processing Sound Pre-training methods have greatly improved the performance of sound event localization and detection (SELD). However, existing Transformer-based models still face high computational cost. To solve this problem, we present a stereo SELD system using a pre-trained PSELDnet and a bidirectional Mamba sequence model. Specifically, we replace the Conformer module with a BiMamba module. We also use asymmetric convolutions to better capture the time and frequency relationships in the audio signal. Test results on the DCASE2025 Task 3 development dataset show that our method performs better than both the baseline and the original PSELDnet with a Conformer decoder. In addition, the proposed model costs fewer computing resources than the baselines. These results show that the BiMamba architecture is effective for solving key challenges in SELD tasks. The source code is publicly accessible at https://github.com/ alexandergwm/DCASE2025 TASK3 Stereo PSELD Mamba. |
| title | Enhancing Stereo Sound Event Detection with BiMamba and Pretrained PSELDnet |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2507.09570 |