3 papers
cs.LG2025
Addressing Representation Collapse in Vector Quantized Models with One Linear Layer
Yongxin Zhu, Bocheng Li, Yifei Xin +2
Vector Quantization (VQ) is essential for discretizing continuous representations in unsupervised learning but suffers from representation collapse, causing low codebook utilizatio…
cs.SD2025
Audio-text Retrieval with Transformer-based Hierarchical Alignment and Disentangled Cross-modal Representation
Yifei Xin, Zhihong Zhu, Xuxin Cheng +2
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 a…
cs.SD2025
Improving Audio-Text Retrieval via Hierarchical Cross-Modal Interaction and Auxiliary Captions
Yifei Xin, Yuexian Zou
Most existing audio-text retrieval (ATR) methods focus on constructing contrastive pairs between whole audio clips and complete caption sentences, while ignoring fine-grained cross…