{"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/self-supervised-fine-tuning-for-improved","title":"Self-supervised Fine-tuning for Improved Content Representations by Speaker-invariant Clustering","arxiv_id":"2305.11072","date":"2023-05-18","proceeding":null,"authors":["Heng-Jui Chang","Alexander H. Liu","James Glass"],"abstract":"Self-supervised speech representation models have succeeded in various tasks, but improving them for content-related problems using unlabeled data is challenging. We propose speaker-invariant clustering (Spin), a novel self-supervised learning method that clusters speech representations and performs swapped prediction between the original and speaker-perturbed utterances. Spin disentangles speaker information and preserves content representations with just 45 minutes of fine-tuning on a single GPU. Spin improves pre-trained networks and outperforms prior methods in speech recognition and acoustic unit discovery.","url_abs":"https://arxiv.org/abs/2305.11072v1","url_pdf":"https://arxiv.org/pdf/2305.11072v1.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":"self-supervised-fine-tuning-for-improved","repo_url":"https://github.com/vectominist/spin","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"Acoustic Unit Discovery"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.11072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11072"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/vectominist/spin","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"9796f8130e50f5a7","entry":"with_incremental_state","repo":"vectominist/spin","repo_kind":"official","path":"s3prl_py/wav2vec2_model.py","file_url":"https://github.com/vectominist/spin/blob/HEAD/s3prl_py/wav2vec2_model.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9796f8130e50f5a7"}},{"code_sha256_prefix":"e2df252c162a4212","entry":"apply_rotary_pos_emb","repo":"vectominist/spin","repo_kind":"official","path":"s3prl_py/wav2vec2_model.py","file_url":"https://github.com/vectominist/spin/blob/HEAD/s3prl_py/wav2vec2_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e2df252c162a4212"}},{"code_sha256_prefix":"d22a5e7495dd7a3a","entry":"compute_mask_indices","repo":"vectominist/spin","repo_kind":"official","path":"s3prl_py/WavLM.py","file_url":"https://github.com/vectominist/spin/blob/HEAD/s3prl_py/WavLM.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d22a5e7495dd7a3a"}},{"code_sha256_prefix":"766ad0e51b7a8f09","entry":"rotate_half","repo":"vectominist/spin","repo_kind":"official","path":"s3prl_py/wav2vec2_model.py","file_url":"https://github.com/vectominist/spin/blob/HEAD/s3prl_py/wav2vec2_model.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"766ad0e51b7a8f09"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}