Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Yu, Zhu, Hongxu, Wang, Jiadong, Chen, Kainan, Qian, Xinyuan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2507.07384
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911093532655616
author Chen, Yu
Zhu, Hongxu
Wang, Jiadong
Chen, Kainan
Qian, Xinyuan
author_facet Chen, Yu
Zhu, Hongxu
Wang, Jiadong
Chen, Kainan
Qian, Xinyuan
contents Audio-visual sound source localization (AV-SSL) estimates the position of sound sources by fusing auditory and visual cues. Current AV-SSL methodologies typically require spatially-paired audio-visual data and cannot selectively localize specific target sources. To address these limitations, we introduce Cross-Instance Audio-Visual Localization (CI-AVL), a novel task that localizes target sound sources using visual prompts from different instances of the same semantic class. CI-AVL enables selective localization without spatially paired data. To solve this task, we propose AV-SSAN, a semantic-spatial alignment framework centered on a Multi-Band Semantic-Spatial Alignment Network (MB-SSA Net). MB-SSA Net decomposes the audio spectrogram into multiple frequency bands, aligns each band with semantic visual prompts, and refines spatial cues to estimate the direction-of-arrival (DoA). To facilitate this research, we construct VGGSound-SSL, a large-scale dataset comprising 13,981 spatial audio clips across 296 categories, each paired with visual prompts. AV-SSAN achieves a mean absolute error of 16.59 and an accuracy of 71.29%, significantly outperforming existing AV-SSL methods. Code and data will be public.
format Preprint
id arxiv_https___arxiv_org_abs_2507_07384
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AV-SSAN: Audio-Visual Selective DoA Estimation through Explicit Multi-Band Semantic-Spatial Alignment
Chen, Yu
Zhu, Hongxu
Wang, Jiadong
Chen, Kainan
Qian, Xinyuan
Sound
Audio and Speech Processing
Audio-visual sound source localization (AV-SSL) estimates the position of sound sources by fusing auditory and visual cues. Current AV-SSL methodologies typically require spatially-paired audio-visual data and cannot selectively localize specific target sources. To address these limitations, we introduce Cross-Instance Audio-Visual Localization (CI-AVL), a novel task that localizes target sound sources using visual prompts from different instances of the same semantic class. CI-AVL enables selective localization without spatially paired data. To solve this task, we propose AV-SSAN, a semantic-spatial alignment framework centered on a Multi-Band Semantic-Spatial Alignment Network (MB-SSA Net). MB-SSA Net decomposes the audio spectrogram into multiple frequency bands, aligns each band with semantic visual prompts, and refines spatial cues to estimate the direction-of-arrival (DoA). To facilitate this research, we construct VGGSound-SSL, a large-scale dataset comprising 13,981 spatial audio clips across 296 categories, each paired with visual prompts. AV-SSAN achieves a mean absolute error of 16.59 and an accuracy of 71.29%, significantly outperforming existing AV-SSL methods. Code and data will be public.
title AV-SSAN: Audio-Visual Selective DoA Estimation through Explicit Multi-Band Semantic-Spatial Alignment
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.07384