Saved in:
Bibliographic Details
Main Authors: Hu, Jinbo, Cao, Yin, Wu, Ming, Luo, Zhenbo, Yang, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.16724
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918143582011392
author Hu, Jinbo
Cao, Yin
Wu, Ming
Luo, Zhenbo
Yang, Jun
author_facet Hu, Jinbo
Cao, Yin
Wu, Ming
Luo, Zhenbo
Yang, Jun
contents Spatial audio understanding is essential for accurately perceiving and interpreting acoustic environments. However, existing audio-language models exhibit limitations in processing spatial audio and perceiving spatial acoustic scenes. To address this gap, we propose the Spatial Audio Language Model (SALM), a novel framework that bridges spatial audio and language through multi-modal contrastive learning. SALM integrates a text encoder with a dual-branch audio encoder that decomposes spatial sound into semantic and spatial components via structured audio embeddings. Key features of SALM include seamless alignment between spatial audio and natural language, both separate and joint extraction of spatial and semantic representations, zero-shot direction classification, and flexible support for spatial audio editing. Experimental results demonstrate that SALM effectively captures and aligns cross-modal representations, yielding well-structured audio embeddings. Furthermore, SALM enables advanced editing capabilities, such as modifying directional audio using text-based embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing
Hu, Jinbo
Cao, Yin
Wu, Ming
Luo, Zhenbo
Yang, Jun
Sound
Audio and Speech Processing
Spatial audio understanding is essential for accurately perceiving and interpreting acoustic environments. However, existing audio-language models exhibit limitations in processing spatial audio and perceiving spatial acoustic scenes. To address this gap, we propose the Spatial Audio Language Model (SALM), a novel framework that bridges spatial audio and language through multi-modal contrastive learning. SALM integrates a text encoder with a dual-branch audio encoder that decomposes spatial sound into semantic and spatial components via structured audio embeddings. Key features of SALM include seamless alignment between spatial audio and natural language, both separate and joint extraction of spatial and semantic representations, zero-shot direction classification, and flexible support for spatial audio editing. Experimental results demonstrate that SALM effectively captures and aligns cross-modal representations, yielding well-structured audio embeddings. Furthermore, SALM enables advanced editing capabilities, such as modifying directional audio using text-based embeddings.
title SALM: Spatial Audio Language Model with Structured Embeddings for Understanding and Editing
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2507.16724