paper-with-me

Papers

ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval

2025-12-11 · Siyuan Fu, Xuchen Guo, Mingjun Liu, Hongxiang Li, Boyin Tan, Gongxi Zhu, Xianwei Zhuang, Jinghan Ru, Yuxin Xie, Yuguo Yin arxiv

The dominant paradigm for Audio-Text Retrieval (ATR) relies on dual-encoder architectures optimized via mini-batch contrastive learning. However, restricting optimization to local in-batch samples creates a fundamental limitation we term the Gradient Locality Bottleneck (GLB), which prevents the resolution of acoustic ambiguities and hinders the learning of rare long-tail concepts. While external knowledge injection can break this bottleneck, it often triggers a problem called Representation-Drift Mismatch (RDM), where a static knowledge base becomes misaligned with evolving encoders, degrading guidance into noise. To address these intertwined challenges, we propose the Adaptive Self-improving Knowledge (ASK) framework. ASK breaks the GLB via multi-grained knowledge injection and mitigates RDM through a dynamic refinement strategy that synchronizes the knowledge base with the model. Additionally, an adaptive reliability weighting scheme is employed to filter retrieval noise based on cross-modal consistency. Extensive experiments across multiple benchmarks demonstrate that ASK consistently achieves new state-of-the-art performance across various backbones.

📄 PDF Abstract BibTeX arXiv:2512.19703

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningText Retrieval

Similar Papers 제목 키워드 기반

Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models

2025-02-27 · Rui Hu, Delai Qiu, Shuyu Wei, Jiaming Zhang 외

Omnimodal Large Language Models (OLLMs) have shown significant progress in integrating vision and text, but still struggle with integrating vision and audio, often exhibiting suboptimal performance when processing audio …

Knowledge DistillationSelf-Knowledge Distillation

AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining

2023-08-10 · Haohe Liu, Yi Yuan, Xubo Liu, Xinhao Mei 외

Although audio generation shares commonalities across different types of audio, such as speech, music, and sound effects, designing models for each type requires careful consideration of specific objectives and biases th…

Audio GenerationIn-Context LearningRepresentation LearningText-to-Music Generation+2

Hearing and Seeing Through CLIP: A Framework for Self-Supervised Sound Source Localization

2025-05-08 · Sooyoung Park, Arda Senocak, Joon Son Chung

Large-scale vision-language models demonstrate strong multimodal alignment and generalization across diverse tasks. Among them, CLIP stands out as one of the most successful approaches. In this work, we extend the applic…

Scene UnderstandingSound Source Localization

Audio Self-supervised Learning: A Survey

2022-03-02 · Shuo Liu, Adria Mallol-Ragolta, Emilia Parada-Cabeleiro, Kun Qian 외

Inspired by the humans' cognitive ability to generalise knowledge and skills, Self-Supervised Learning (SSL) targets at discovering general representations from large-scale data without requiring human annotations, which…

Self-Supervised LearningSurvey

S-SONDO: Self-Supervised Knowledge Distillation for General Audio Foundation Models

2026-04-27 · Mohammed Ali El Adlouni, Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters 외 arxiv

General audio foundation models have recently achieved remarkable progress, enabling strong performance across diverse tasks. However, state-of-the-art models remain extremely large, often with hundreds of millions of pa…

Knowledge DistillationModel Compression