arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.09256cs.SDeess.AS
收藏

基于Transformer的层次对齐与解耦跨模态表示的音频-文本检索

Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation

YifeiXin(西菲·欣);ZhihongZhu(朱之宏);XuxinCheng(程旭鑫);XushengYang(杨旭生);YuexianZou(邹岳先)

Yifei Xin, Zhihong Zhu, Xuxin Cheng, Xusheng Yang, Yuexian Zou

AI总结:

本文提出基于双流Transformer与层次对齐模块的音频-文本检索框架,并引入解耦跨模态表示和置信度感知模块实现细粒度语义对齐,实验证明其有效提升检索性能。

摘要:

现有的大多数音频-文本检索(ATR)方法通常依赖单一层次的交互来关联音频和文本,这限制了它们对齐不同模态的能力,并导致匹配结果不够理想。在本工作中,我们提出了一种新颖的ATR框架,该框架利用双流Transformer结合层次对齐(THA)模块,识别音频与文本之间不同Transformer块的多层次对应关系。此外,当前的ATR方法主要关注学习全局层次的表示,忽略了捕捉与文本语义相对应的音频事件的复杂细节。为弥补这一不足,我们引入了一种解耦跨模态表示(DCR)方法,将高维特征解耦为紧凑的潜在因子,以捕捉细粒度的音频-文本语义关联。此外,我们开发了一个置信度感知(CA)模块,用于估计每对潜在因子的置信度,并自适应地聚合跨模态潜在因子以实现局部语义对齐。实验表明,我们的THA有效提升了ATR性能,DCR方法进一步带来了持续的性能增益。

英文摘要:

Most existing audio-text retrieval (ATR) approaches typically rely on a single-level interaction to associate audio and text, limiting their ability to align different modalities and leading to suboptimal matches. In this work, we present a novel ATR framework that leverages two-stream Transformers in conjunction with a Hierarchical Alignment (THA) module to identify multi-level correspondences of different Transformer blocks between audio and text. Moreover, current ATR methods mainly focus on learning a global-level representation, missing out on intricate details to capture audio occurrences that correspond to textual semantics. To bridge this gap, we introduce a Disentangled Cross-modal Representation (DCR) approach that disentangles high-dimensional features into compact latent factors to grasp fine-grained audio-text semantic correlations. Additionally, we develop a confidence-aware (CA) module to estimate the confidence of each latent factor pair and adaptively aggregate cross-modal latent factors to achieve local semantic alignment. Experiments show that our THA effectively boosts ATR performance, with the DCR approach further contributing to consistent performance gains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑