DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917073046732800 |
|---|---|
| author | Li, Haowen Luo, Zhengding Shi, Dongyuan Wang, Boxiang Ji, Junwei Yang, Ziyi Gan, Woon-Seng |
| author_facet | Li, Haowen Luo, Zhengding Shi, Dongyuan Wang, Boxiang Ji, Junwei Yang, Ziyi Gan, Woon-Seng |
| contents | Direction-of-Arrival (DOA) estimation is critical in spatial audio and acoustic signal processing, with wide-ranging applications in real-world. Most existing DOA models are trained on synthetic data by convolving clean speech with room impulse responses (RIRs), which limits their generalizability due to constrained acoustic diversity. In this paper, we revisit DOA estimation using a recently introduced dataset constructed with the assistance of large language models (LLMs), which provides more realistic and diverse spatial audio scenes. We benchmark several representative neural-based DOA methods on this dataset and propose LightDOA, a lightweight DOA estimation model based on depthwise separable convolutions, specifically designed for mutil-channel input in varying environments. Experimental results show that LightDOA achieves satisfactory accuracy and robustness across various acoustic scenes while maintaining low computational complexity. This study not only highlights the potential of spatial audio synthesized with the assistance of LLMs in advancing robust and efficient DOA estimation research, but also highlights LightDOA as efficient solution for resource-constrained applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08012 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes Li, Haowen Luo, Zhengding Shi, Dongyuan Wang, Boxiang Ji, Junwei Yang, Ziyi Gan, Woon-Seng Sound Artificial Intelligence Direction-of-Arrival (DOA) estimation is critical in spatial audio and acoustic signal processing, with wide-ranging applications in real-world. Most existing DOA models are trained on synthetic data by convolving clean speech with room impulse responses (RIRs), which limits their generalizability due to constrained acoustic diversity. In this paper, we revisit DOA estimation using a recently introduced dataset constructed with the assistance of large language models (LLMs), which provides more realistic and diverse spatial audio scenes. We benchmark several representative neural-based DOA methods on this dataset and propose LightDOA, a lightweight DOA estimation model based on depthwise separable convolutions, specifically designed for mutil-channel input in varying environments. Experimental results show that LightDOA achieves satisfactory accuracy and robustness across various acoustic scenes while maintaining low computational complexity. This study not only highlights the potential of spatial audio synthesized with the assistance of LLMs in advancing robust and efficient DOA estimation research, but also highlights LightDOA as efficient solution for resource-constrained applications. |
| title | DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2511.08012 |