English
Related papers

Related papers: Self-Supervised Learning of Audio Representations …

200 papers

Self-supervision methods learn representations by solving pretext tasks that do not require human-generated labels, alleviating the need for time-consuming annotations. These methods have been applied in computer vision, natural language…

Sound · Computer Science 2023-06-27 Giovana Morais , Matthew E. P. Davies , Marcelo Queiroz , Magdalena Fuentes

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…

Sound · Computer Science 2025-09-23 Yang Wang , Qibin Liang , Chenghao Xiao , Yizhi Li , Noura Al Moubayed , Chenghua Lin

Contrastive self-supervised learning has gained attention for its ability to create high-quality representations from large unlabelled data sets. A key reason that these powerful features enable data-efficient learning of downstream tasks…

Machine Learning · Computer Science 2024-01-29 Calum Heggan , Tim Hospedales , Sam Budgett , Mehrdad Yaghoobi

Audio representations for music information retrieval are typically learned via supervised learning in a task-specific fashion. Although effective at producing state-of-the-art results, this scheme lacks flexibility with respect to the…

Sound · Computer Science 2022-02-18 Ilaria Manco , Emmanouil Benetos , Elio Quinton , Gyorgy Fazekas

Self-supervised learning, which benefits from automatically constructing labels through pre-designed pretext task, has recently been applied for strengthen supervised learning. Since previous self-supervised pretext tasks are based on…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Zilin Ding , Yuhang Yang , Xuan Cheng , Xiaomin Wang , Ming Liu

Recently, self-supervised learning methods based on masked latent prediction have proven to encode input data into powerful representations. However, during training, the learned latent space can be further transformed to extract…

Sound · Computer Science 2025-06-05 Aurian Quelennec , Pierre Chouteau , Geoffroy Peeters , Slim Essid

Speech separation has been well developed, with the very successful permutation invariant training (PIT) approach, although the frequent label assignment switching happening during PIT training remains to be a problem when better…

Sound · Computer Science 2021-08-24 Sung-Feng Huang , Shun-Po Chuang , Da-Rong Liu , Yi-Chen Chen , Gene-Ping Yang , Hung-yi Lee

Pretext-based self-supervised learning learns the semantic representation via a handcrafted pretext task over unlabeled data and then uses the learned representation for downstream tasks, which effectively reduces the sample complexity of…

Machine Learning · Computer Science 2022-02-24 Jiaye Teng , Weiran Huang , Haowei He

As the field of deep learning steadily transitions from the realm of academic research to practical application, the significance of self-supervised pretraining methods has become increasingly prominent. These methods, particularly in the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Toni Albert , Bjoern Eskofier , Dario Zanca

In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its…

Computer Vision and Pattern Recognition · Computer Science 2021-06-04 Vladan Stojnić , Vladimir Risojević

We present a multimodal framework to learn general audio representations from videos. Existing contrastive audio representation learning methods mainly focus on using the audio modality alone during training. In this work, we show that…

Sound · Computer Science 2021-04-29 Luyu Wang , Pauline Luc , Adria Recasens , Jean-Baptiste Alayrac , Aaron van den Oord

Multi-pitch estimation is a decades-long research problem involving the detection of pitch activity associated with concurrent musical events within multi-instrument mixtures. Supervised learning techniques have demonstrated solid…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-27 Frank Cwitkowitz , Zhiyao Duan

Self-supervision is one of the hallmarks of representation learning in the increasingly popular suite of foundation models including large language models such as BERT and GPT-3, but it has not been pursued in the context of multivariate…

Machine Learning · Computer Science 2024-02-05 Xiao Shou , Dharmashankar Subramanian , Debarun Bhattacharjya , Tian Gao , Kristin P. Bennet

Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…

Sound · Computer Science 2024-11-06 Julia Wilkins , Sivan Ding , Magdalena Fuentes , Juan Pablo Bello

The success of deep learning based models for computer vision applications requires large scale human annotated data which are often expensive to generate. Self-supervised learning, a subset of unsupervised learning, handles this problem by…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Siladittya Manna , Saumik Bhattacharya , Umapada Pal

We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual…

Computer Vision and Pattern Recognition · Computer Science 2020-11-04 Pedro Morgado , Yi Li , Nuno Vasconcelos

Existing audio analysis methods generally first transform the audio stream to spectrogram, and then feed it into CNN for further analysis. A standard CNN recognizes specific visual patterns over feature map, then pools for high-level…

Sound · Computer Science 2023-03-16 Yulin Pan , Xiangteng He , Biao Gong , Yuxin Peng , Yiliang Lv

Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be…

Machine Learning · Computer Science 2019-01-16 Yan Zhang , Jonathon Hare , Adam Prügel-Bennett

Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate…

Computer Vision and Pattern Recognition · Computer Science 2023-11-22 Akash Kumar , Ashlesha Kumar , Vibhav Vineet , Yogesh Singh Rawat

Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Victor Sechaud , Jérémy Scanvic , Quentin Barthélemy , Patrice Abry , Julián Tachella