{"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/boosting-self-supervised-embeddings-for","title":"Boosting Self-Supervised Embeddings for Speech Enhancement","arxiv_id":"2204.03339","date":"2022-04-07","proceeding":null,"authors":["Kuo-Hsuan Hung","Szu-Wei Fu","Huan-Hsin Tseng","Hsin-Tien Chiang","Yu Tsao","Chii-Wann Lin"],"abstract":"Self-supervised learning (SSL) representation for speech has achieved state-of-the-art (SOTA) performance on several downstream tasks. However, there remains room for improvement in speech enhancement (SE) tasks. In this study, we used a cross-domain feature to solve the problem that SSL embeddings may lack fine-grained information to regenerate speech signals. By integrating the SSL representation and spectrogram, the result can be significantly boosted. We further study the relationship between the noise robustness of SSL representation via clean-noisy distance (CN distance) and the layer importance for SE. Consequently, we found that SSL representations with lower noise robustness are more important. Furthermore, our experiments on the VCTK-DEMAND dataset demonstrated that fine-tuning an SSL representation with an SE model can outperform the SOTA SSL-based SE methods in PESQ, CSIG and COVL without invoking complicated network architectures. In later experiments, the CN distance in SSL embeddings was observed to increase after fine-tuning. These results verify our expectations and may help design SE-related SSL training in the future.","url_abs":"https://arxiv.org/abs/2204.03339v2","url_pdf":"https://arxiv.org/pdf/2204.03339v2.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":"boosting-self-supervised-embeddings-for","repo_url":"https://github.com/khhungg/BSSE-SE","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-enhancement-on-demand","task":"Speech Enhancement","dataset":"VoiceBank + DEMAND","model":"BSSE-SE","rank_in_archive_order":22,"of":42,"metrics":{"CBAK":"3.58","COVL":"3.88","CSIG":"4.52","PESQ (wb)":"3.20","STOI":"95.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.03339","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03339"}},"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/khhungg/BSSE-SE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"f6b944f50d3f15ae","entry":"count_parameters","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"Load_model.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/Load_model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"f30ebf4e48b7e2d7","entry":"gelu","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"models/modules.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/models/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"code_sha256_prefix":"d22a5e7495dd7a3a","entry":"compute_mask_indices","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"models/WavLM.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/models/WavLM.py","link_basis":"harvester_set","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":"4aa7333ffd7e18c6","entry":"gelu_accurate","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"models/modules.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/models/modules.py","link_basis":"harvester_set","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":"4aa7333ffd7e18c6"}},{"code_sha256_prefix":"01233f4856456c5f","entry":"get_activation_fn","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"models/modules.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/models/modules.py","link_basis":"harvester_set","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":"01233f4856456c5f"}},{"code_sha256_prefix":"9431561d729dfc68","entry":"get_filepaths","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"util.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/util.py","link_basis":"harvester_set","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":"9431561d729dfc68"}},{"code_sha256_prefix":"f63be0bf29f7515a","entry":"init_kernels","repo":"khhungg/BSSE-SE","repo_kind":"official","path":"conv_stft.py","file_url":"https://github.com/khhungg/BSSE-SE/blob/HEAD/conv_stft.py","link_basis":"harvester_set","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":"f63be0bf29f7515a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}