Generating Diverse Audio-Visual 360 Soundscapes for Sound Event Localization and Detection
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_ | 1866915226528514048 |
|---|---|
| author | Roman, Adrian S. Chang, Aiden Meza, Gerardo Roman, Iran R. |
| author_facet | Roman, Adrian S. Chang, Aiden Meza, Gerardo Roman, Iran R. |
| contents | We present SELDVisualSynth, a tool for generating synthetic videos for audio-visual sound event localization and detection (SELD). Our approach incorporates real-world background images to improve realism in synthetic audio-visual SELD data while also ensuring audio-visual spatial alignment. The tool creates 360 synthetic videos where objects move matching synthetic SELD audio data and its annotations. Experimental results demonstrate that a model trained with this data attains performance gains across multiple metrics, achieving superior localization recall (56.4 LR) and competitive localization error (21.9deg LE). We open-source our data generation tool for maximal use by members of the SELD research community. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02988 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generating Diverse Audio-Visual 360 Soundscapes for Sound Event Localization and Detection Roman, Adrian S. Chang, Aiden Meza, Gerardo Roman, Iran R. Sound Audio and Speech Processing We present SELDVisualSynth, a tool for generating synthetic videos for audio-visual sound event localization and detection (SELD). Our approach incorporates real-world background images to improve realism in synthetic audio-visual SELD data while also ensuring audio-visual spatial alignment. The tool creates 360 synthetic videos where objects move matching synthetic SELD audio data and its annotations. Experimental results demonstrate that a model trained with this data attains performance gains across multiple metrics, achieving superior localization recall (56.4 LR) and competitive localization error (21.9deg LE). We open-source our data generation tool for maximal use by members of the SELD research community. |
| title | Generating Diverse Audio-Visual 360 Soundscapes for Sound Event Localization and Detection |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2504.02988 |