{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/conformer-based-self-supervised-learning-for","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","arxiv_id":"2110.07313","date":"2021-10-14","proceeding":null,"authors":["Sangeeta Srivastava","Yun Wang","Andros Tjandra","Anurag Kumar","Chunxi Liu","Kritika Singh","Yatharth Saraf"],"abstract":"Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have comprehensively analyzed audio representation learning for non-speech audio tasks. In this paper, we propose a self-supervised audio representation learning method and apply it to a variety of downstream non-speech audio tasks. We combine the well-known wav2vec 2.0 framework, which has shown success in self-supervised learning for speech tasks, with parameter-efficient conformer architectures. Our self-supervised pre-training can reduce the need for labeled data by two-thirds. On the AudioSet benchmark, we achieve a mean average precision (mAP) score of 0.415, which is a new state-of-the-art on this dataset through audio-only self-supervised learning. Our fine-tuned conformers also surpass or match the performance of previous systems pre-trained in a supervised way on several downstream tasks. We further discuss the important design considerations for both pre-training and fine-tuning.","url_abs":"https://arxiv.org/abs/2110.07313v3","url_pdf":"https://arxiv.org/pdf/2110.07313v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-representation-learning","task_name":"Speech Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-audioset","task":"Audio Classification","dataset":"AudioSet","model":"Conformer (AS-2M)","rank_in_archive_order":43,"of":51,"metrics":{"Test mAP":"0.411"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-balanced-audio-set","task":"Audio Classification","dataset":"Balanced Audio Set","model":"Conformer","rank_in_archive_order":8,"of":8,"metrics":{"Mean AP":"27.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.07313","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}