paper-with-me

Papers

CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction

2024-02-27 · Hao Ma, Zhiyuan Peng, Xu Li, Mingjie Shao, Xixin Wu, Ju Liu

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that converts user queries into conditional embeddings, and a separation network that extracts the target sound accordingly. Existing methods commonly train models from scratch. As a consequence, substantial data and computational resources are required to make the randomly initialized model comprehend sound events and perform separation accordingly. In this paper, we propose to integrate pre-trained models into TSE models to address the above issue. To be specific, we tailor and adapt the powerful contrastive language-audio pre-trained model (CLAP) for USS, denoted as CLAPSep. CLAPSep also accepts flexible user inputs, taking both positive and negative user prompts of uni- and/or multi-modalities for target sound extraction. These key features of CLAPSep can not only enhance the extraction performance but also improve the versatility of its application. We provide extensive experiments on 5 diverse datasets to demonstrate the superior performance and zero- and few-shot generalizability of our proposed CLAPSep with fast training convergence, surpassing previous methods by a significant margin. Full codes and some audio examples are released for reproduction and evaluation.

📄 PDF Abstract BibTeX arXiv:2402.17455

Code (1)

aisaka0v0/clapsep 공식 구현 pytorch

Tasks

Target Sound Extraction

Similar Papers 제목 키워드 기반

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data

2024-01-16 · Yuhui Zhang, Elaine Sui, Serena Yeung-Levy

Building cross-modal applications is challenging due to limited paired multi-modal data. Recent works have shown that leveraging a pre-trained multi-modal contrastive representation space enables cross-modal tasks to be …

Image GenerationText to Image GenerationText-to-Image GenerationVideo Captioning

Understanding the Gain from Data Filtering in Multimodal Contrastive Learning

2025-12-16 · Divyansh Pareek, Sewoong Oh, Simon S. Du arxiv

The success of modern multimodal representation learning relies on internet-scale datasets. Due to the low quality of a large fraction of raw web data, data curation has become a critical step in the training pipeline. F…

Representation LearningContrastive Learning

Continual Multimodal Contrastive Learning

2025-03-19 · Xiaohao Liu, Xiaobo Xia, See-Kiong Ng, Tat-Seng Chua

Multimodal contrastive learning (MCL) advances in aligning different modalities and generating multimodal representations in a joint space. By leveraging contrastive learning across diverse modalities, large-scale multim…

Continual LearningContrastive Learning

Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition

2022-05-20 · Razvan Brinzea, Bulat Khaertdinov, Stylianos Asteriadis

Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. W…

Activity RecognitionContrastive LearningHuman Activity RecognitionRetrieval+1

Multimodal LLMs under Pairwise Modalities

2026-05-20 · Yan Li, Yunlong Deng, Yuewen Sun, Gongxu Luo 외 arxiv

Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned d…

Representation LearningContrastive LearningPoint Clouds