{"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/atst-audio-representation-learning-with","title":"ATST: Audio Representation Learning with Teacher-Student Transformer","arxiv_id":"2204.12076","date":"2022-04-26","proceeding":null,"authors":["Xian Li","Xiaofei Li"],"abstract":"Self-supervised learning (SSL) learns knowledge from a large amount of unlabeled data, and then transfers the knowledge to a specific problem with a limited number of labeled data. SSL has achieved promising results in various domains. This work addresses the problem of segment-level general audio SSL, and proposes a new transformer-based teacher-student SSL model, named ATST. A transformer encoder is developed on a recently emerged teacher-student baseline scheme, which largely improves the modeling capability of pre-training. In addition, a new strategy for positive pair creation is designed to fully leverage the capability of transformer. Extensive experiments have been conducted, and the proposed model achieves the new state-of-the-art results on almost all of the downstream tasks.","url_abs":"https://arxiv.org/abs/2204.12076v3","url_pdf":"https://arxiv.org/pdf/2204.12076v3.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":[{"paper_slug":"atst-audio-representation-learning-with","repo_url":"https://github.com/Audio-WestlakeU/audiossl/tree/main/audiossl/methods/atst","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"atst-audio-representation-learning-with","repo_url":"https://github.com/Audio-WestlakeU/ATST-SED","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"atst-audio-representation-learning-with","repo_url":"https://github.com/2023-MindSpore-4/Code8/tree/main/ats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"atst-audio-representation-learning-with","repo_url":"https://github.com/2024-MindSpore-1/Code6/tree/main/ats","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"instrument-recognition","task_name":"Instrument Recognition"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-audio-classification","task_name":"Self-Supervised Audio Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speaker-identification","task_name":"Speaker Identification"},{"task_slug":"spoken-command-recognition","task_name":"Spoken Command Recognition"}],"methods":[{"method_slug":"byol","method_name":"BYOL"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-balanced-audio-set","task":"Audio Classification","dataset":"Balanced Audio Set","model":"Base (ours)","rank_in_archive_order":5,"of":8,"metrics":{"Mean AP":"37.4"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-identification-on-voxceleb1","task":"Speaker Identification","dataset":"VoxCeleb1","model":"ATST Base (ours)","rank_in_archive_order":6,"of":12,"metrics":{"Accuracy":"94.3","Top-1 (%)":"94.3"},"uses_additional_data":true},{"leaderboard":"/sota/spoken-command-recognition-on-speech-command","task":"Spoken Command Recognition","dataset":"Speech Command v2","model":"Base (ours)","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"98.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.12076","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}