{"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/on-the-utility-of-self-supervised-models-for","title":"On the Utility of Self-supervised Models for Prosody-related Tasks","arxiv_id":"2210.07185","date":"2022-10-13","proceeding":null,"authors":["Guan-Ting Lin","Chi-Luen Feng","Wei-Ping Huang","Yuan Tseng","Tzu-Han Lin","Chen-An Li","Hung-Yi Lee","Nigel G. Ward"],"abstract":"Self-Supervised Learning (SSL) from speech data has produced models that have achieved remarkable performance in many tasks, and that are known to implicitly represent many aspects of information latently present in speech signals. However, relatively little is known about the suitability of such models for prosody-related tasks or the extent to which they encode prosodic information. We present a new evaluation framework, SUPERB-prosody, consisting of three prosody-related downstream tasks and two pseudo tasks. We find that 13 of the 15 SSL models outperformed the baseline on all the prosody-related tasks. We also show good performance on two pseudo tasks: prosody reconstruction and future prosody prediction. We further analyze the layerwise contributions of the SSL models. Overall we conclude that SSL speech models are highly effective for prosody-related tasks.","url_abs":"https://arxiv.org/abs/2210.07185v2","url_pdf":"https://arxiv.org/pdf/2210.07185v2.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":"on-the-utility-of-self-supervised-models-for","repo_url":"https://github.com/jsalt-2022-ssl/superb-prosody","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"prosody-prediction","task_name":"Prosody Prediction"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.07185","atlas_url":"https://app.syntology.ai/?focus=2210.07185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.07185"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jsalt-2022-ssl/superb-prosody","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"017e86bd00a963bc","entry":"compare","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/utility/get_best_score.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/utility/get_best_score.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"017e86bd00a963bc"}},{"code_sha256_prefix":"28936c41e64792bd","entry":"get_cosine_schedule_with_warmup","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/schedulers.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/schedulers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"28936c41e64792bd"}},{"code_sha256_prefix":"a9a4422e7a95a010","entry":"get_cosine_with_hard_restarts_schedule_with_warmup","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/schedulers.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/schedulers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9a4422e7a95a010"}},{"code_sha256_prefix":"cecd81dc06f43149","entry":"get_grouped_parameters","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/optimizers.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/optimizers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cecd81dc06f43149"}},{"code_sha256_prefix":"1f49d1de2055d4d2","entry":"get_downstream_model","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/downstream/model.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/downstream/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f49d1de2055d4d2"}},{"code_sha256_prefix":"15a4c381f6af50fb","entry":"get_optimizer","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/optimizers.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/optimizers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15a4c381f6af50fb"}},{"code_sha256_prefix":"880bf296f53cdebf","entry":"get_scheduler","repo":"jsalt-2022-ssl/superb-prosody","repo_kind":"official","path":"s3prl/schedulers.py","file_url":"https://github.com/jsalt-2022-ssl/superb-prosody/blob/HEAD/s3prl/schedulers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"880bf296f53cdebf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}