Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations
Improving generalization is a major challenge in audio classification due to labeled data scarcity. Self-supervised learning (SSL) methods tackle this by leveraging unlabeled data to learn useful features for downstream classification tasks. In this work, we propose an augmented contrastive SSL framework to learn invariant representations from unlabeled data. Our method applies various perturbations to the unlabeled input data and utilizes contrastive learning to learn representations robust to such perturbations. Experimental results on the Audioset and DESED datasets show that our framework significantly outperforms state-of-the-art SSL and supervised learning methods on sound/event classification tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Audio ClassificationClassificationContrastive LearningSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Anomalous Sound Detection using Audio Representation with Machine ID based Contrastive Learning Pretraining
Existing contrastive learning methods for anomalous sound detection refine the audio representation of each audio sample by using the contrast between the samples' augmentations (e.g., with time or frequency masking). Ho…
Anomaly DetectionContrastive LearningA Framework for Generative and Contrastive Learning of Audio Representations
In this paper, we present a framework for contrastive learning for audio representations, in a self supervised frame work without access to any ground truth labels. The core idea in self supervised contrastive learning i…
Contrastive LearningA Generic Self-Supervised Framework of Learning Invariant Discriminative Features
Self-supervised learning (SSL) has become a popular method for generating invariant representations without the need for human annotations. Nonetheless, the desired invariant representation is achieved by utilising prior…
Contrastive LearningDimensionality ReductionRepresentation LearningSelf-Supervised LearningFLAP: Fast Language-Audio Pre-training
We propose Fast Language-Audio Pre-training (FLAP), a self-supervised approach that efficiently and effectively learns aligned audio and language representations through masking, contrastive learning and reconstruction. …
AudioCapsContrastive LearningRetrievalText RetrievalSelf-supervised learning of audio representations using angular contrastive loss
In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically si…
Contrastive LearningSelf-Supervised Learning