paper-with-me

홈 › Papers

Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation

2023-09-27 · Xilin Jiang, Cong Han, Yinghao Aaron Li, Nima Mesgarani

In this study, we present a simple multi-channel framework for contrastive learning (MC-SimCLR) to encode 'what' and 'where' of spatial audios. MC-SimCLR learns joint spectral and spatial representations from unlabeled spatial audios, thereby enhancing both event classification and sound localization in downstream tasks. At its core, we propose a multi-level data augmentation pipeline that augments different levels of audio features, including waveforms, Mel spectrograms, and generalized cross-correlation (GCC) features. In addition, we introduce simple yet effective channel-wise augmentation methods to randomly swap the order of the microphones and mask Mel and GCC channels. By using these augmentations, we find that linear layers on top of the learned representation significantly outperform supervised models in terms of both event classification accuracy and localization error. We also perform a comprehensive analysis of the effect of each augmentation method and a comparison of the fine-tuning performance using different amounts of labeled data.

📄 PDF Abstract BibTeX arXiv:2309.15938

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningData Augmentation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Multi-organ Self-supervised Contrastive Learning for Breast Lesion Segmentation

2024-02-21 · Hugo Figueiras, Helena Aidos, Nuno Cruz Garcia

Self-supervised learning has proven to be an effective way to learn representations in domains where annotated labels are scarce, such as medical imaging. A widely adopted framework for this purpose is contrastive learni…

Contrastive LearningLesion SegmentationSelf-Supervised Learning

Towards Objective Obstetric Ultrasound Assessment: Contrastive Representation Learning for Fetal Movement Detection

2025-10-23 · Talha Ilyas, Duong Nhu, Allison Thomas, Arie Levin 외 arxiv

Accurate fetal movement (FM) detection is essential for assessing prenatal health, as abnormal movement patterns can indicate underlying complications such as placental dysfunction or fetal distress. Traditional methods,…

Self-Supervised LearningRepresentation LearningContrastive Learning

Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification

2021-05-17 · Hao Xue, Flora D. Salim

The usage of smartphone-collected respiratory sound, trained with deep learning models, for detecting and classifying COVID-19 becomes popular recently. It removes the need for in-person testing procedures especially for…

ClassificationCough ClassificationDiagnosticSelf-Supervised Learning

Self-supervised Contrastive Learning for Audio-Visual Action Recognition

2022-04-28 · Yang Liu, Ying Tan, Haoyuan Lan

The underlying correlation between audio and visual modalities can be utilized to learn supervised information for unlabeled videos. In this paper, we propose an end-to-end self-supervised framework named Audio-Visual Co…

Action RecognitionContrastive LearningSelf-Supervised Action Recognition

Unsupervised Contrastive Learning of Sound Event Representations

2020-11-15 · Eduardo Fonseca, Diego Ortego, Kevin McGuinness, Noel E. O'Connor 외

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore u…

Contrastive LearningLinear evaluationRepresentation Learning