Language-based Audio Retrieval with Co-Attention Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Haoran, Wang, Zimu, Chen, Qiuyi, Chen, Jianjun, Wang, Jia, Zhang, Haiyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915085506576384
author Sun, Haoran
Wang, Zimu
Chen, Qiuyi
Chen, Jianjun
Wang, Jia
Zhang, Haiyang
author_facet Sun, Haoran
Wang, Zimu
Chen, Qiuyi
Chen, Jianjun
Wang, Jia
Zhang, Haiyang
contents In recent years, user-generated audio content has proliferated across various media platforms, creating a growing need for efficient retrieval methods that allow users to search for audio clips using natural language queries. This task, known as language-based audio retrieval, presents significant challenges due to the complexity of learning semantic representations from heterogeneous data across both text and audio modalities. In this work, we introduce a novel framework for the language-based audio retrieval task that leverages co-attention mechanismto jointly learn meaningful representations from both modalities. To enhance the model's ability to capture fine-grained cross-modal interactions, we propose a cascaded co-attention architecture, where co-attention modules are stacked or iterated to progressively refine the semantic alignment between text and audio. Experiments conducted on two public datasets show that the proposed method can achieve better performance than the state-of-the-art method. Specifically, our best performed co-attention model achieves a 16.6% improvement in mean Average Precision on Clotho dataset, and a 15.1% improvement on AudioCaps.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20914
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Language-based Audio Retrieval with Co-Attention Networks
Sun, Haoran
Wang, Zimu
Chen, Qiuyi
Chen, Jianjun
Wang, Jia
Zhang, Haiyang
Sound
Information Retrieval
Audio and Speech Processing
In recent years, user-generated audio content has proliferated across various media platforms, creating a growing need for efficient retrieval methods that allow users to search for audio clips using natural language queries. This task, known as language-based audio retrieval, presents significant challenges due to the complexity of learning semantic representations from heterogeneous data across both text and audio modalities. In this work, we introduce a novel framework for the language-based audio retrieval task that leverages co-attention mechanismto jointly learn meaningful representations from both modalities. To enhance the model's ability to capture fine-grained cross-modal interactions, we propose a cascaded co-attention architecture, where co-attention modules are stacked or iterated to progressively refine the semantic alignment between text and audio. Experiments conducted on two public datasets show that the proposed method can achieve better performance than the state-of-the-art method. Specifically, our best performed co-attention model achieves a 16.6% improvement in mean Average Precision on Clotho dataset, and a 15.1% improvement on AudioCaps.
title Language-based Audio Retrieval with Co-Attention Networks
topic Sound
Information Retrieval
Audio and Speech Processing
url https://arxiv.org/abs/2412.20914