paper-with-me

홈 › Papers

Audio Contrastive based Fine-tuning

2023-09-21 · Yang Wang, Qibin Liang, Chenghao Xiao, Yizhi Li, Noura Al Moubayed, Chenghua Lin

Audio classification plays a crucial role in speech and sound processing tasks with a wide range of applications. There still remains a challenge of striking the right balance between fitting the model to the training data (avoiding overfitting) and enabling it to generalise well to a new domain. Leveraging the transferability of contrastive learning, we introduce Audio Contrastive-based Fine-tuning (AudioConFit), an efficient approach characterised by robust generalisability. Empirical experiments on a variety of audio classification tasks demonstrate the effectiveness and robustness of our approach, which achieves state-of-the-art results in various settings.

📄 PDF Abstract BibTeX arXiv:2309.11895

Code (0)

등록된 구현이 없습니다.

Tasks

Audio ClassificationContrastive Learning

Similar Papers 제목 키워드 기반

Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning

2025-12-22 · Apoorv Vyas, Heng-Jui Chang, Cheng-Fu Yang, Po-Yao Huang 외 arxiv

We introduce Perception Encoder Audiovisual, PE-AV, a new family of encoders for audio and video understanding trained with scaled contrastive learning. Built on PE, PE-AV makes several key contributions to extend repres…

Sound Event DetectionContrastive Learning

AudioMosaic: Contrastive Masked Audio Representation Learning

2026-05-14 · Hanxun Huang, Qizhou Wang, Xingjun Ma, Cihang Xie 외 arxiv

Audio self-supervised learning (SSL) aims to learn general-purpose representations from large-scale unlabeled audio data. While recent advances have been driven mainly by generative reconstruction objectives, contrastive…

Self-Supervised LearningRepresentation LearningContrastive Learning

Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining

2024-08-21 · Jonathan Greif, Florian Schmid, Paul Primus, Gerhard Widmer

Query-by-Vocal Imitation (QBV) is about searching audio files within databases using vocal imitations created by the user's voice. Since most humans can effectively communicate sound concepts through voice, QBV offers th…

Contrastive Learning

Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss

2026-06-29 · Nian Shao, Xian Li, Xiaofei Li arxiv

Sound event detection (SED) is a core module for acoustic environmental analysis, yet its performance is often limited by scarce labeled data. Recent systems leverage large pretrained audio foundation models, but effecti…

Sound Event DetectionContrastive Learning

Towards Attention-based Contrastive Learning for Audio Spoof Detection

2024-07-03 · Chirag Goel, Surya Koppisetti, Ben Colman, Ali Shahriyari 외

Vision transformers (ViT) have made substantial progress for classification tasks in computer vision. Recently, Gong et. al. '21, introduced attention-based modeling for several audio tasks. However, relatively unexplore…

Contrastive LearningRepresentation Learning