{"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/singer-identity-representation-learning-using-1","title":"Singer Identity Representation Learning using Self-Supervised Techniques","arxiv_id":"2401.05064","date":"2024-01-10","proceeding":"International Society of Music Information Retrieval 2023 8","authors":["Bernardo Torres","Stefan Lattner","Gaël Richard"],"abstract":"Significant strides have been made in creating voice identity representations using speech data. However, the same level of progress has not been achieved for singing voices. To bridge this gap, we suggest a framework for training singer identity encoders to extract representations suitable for various singing-related tasks, such as singing voice similarity and synthesis. We explore different self-supervised learning techniques on a large collection of isolated vocal tracks and apply data augmentations during training to ensure that the representations are invariant to pitch and content variations. We evaluate the quality of the resulting representations on singer similarity and identification tasks across multiple datasets, with a particular emphasis on out-of-domain generalization. Our proposed framework produces high-quality embeddings that outperform both speaker verification and wav2vec 2.0 pre-trained baselines on singing voice while operating at 44.1 kHz. We release our code and trained models to facilitate further research on singing voice and related areas.","url_abs":"https://arxiv.org/abs/2401.05064v1","url_pdf":"https://arxiv.org/pdf/2401.05064v1.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":"singer-identity-representation-learning-using-1","repo_url":"https://github.com/SonyCSLParis/ssl-singer-identity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speaker-verification","task_name":"Speaker Verification"},{"task_slug":"voice-similarity","task_name":"Voice Similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.05064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05064"}},"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/SonyCSLParis/ssl-singer-identity","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":8,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"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":"3b932b18b287d638","entry":"covariance","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/losses.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b932b18b287d638"}},{"code_sha256_prefix":"f4e36163a59bccb6","entry":"get_vision_backbone","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/models/network_components.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/models/network_components.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4e36163a59bccb6"}},{"code_sha256_prefix":"df42352bfd35bda6","entry":"normalize_signal","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/data_utils.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df42352bfd35bda6"}},{"code_sha256_prefix":"865df4f8fa0dee96","entry":"roll","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/core.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"865df4f8fa0dee96"}},{"code_sha256_prefix":"214b8108ac54e882","entry":"sim_cos","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/core.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"214b8108ac54e882"}},{"code_sha256_prefix":"b3c544fffba435b4","entry":"similarity","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/core.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3c544fffba435b4"}},{"code_sha256_prefix":"d92e45e02cbf7ea3","entry":"std_batch","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/losses.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d92e45e02cbf7ea3"}},{"code_sha256_prefix":"29168330d3c071e5","entry":"variance_hinge_reg","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/losses.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"29168330d3c071e5"}},{"code_sha256_prefix":"1160558ca3846ea8","entry":"fetch","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/fetch_pretrained.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/fetch_pretrained.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":"1160558ca3846ea8"}},{"code_sha256_prefix":"4702a5df119164ef","entry":"from_hparams","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/fetch_pretrained.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/fetch_pretrained.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":"4702a5df119164ef"}},{"code_sha256_prefix":"df84f474cafaa6b7","entry":"from_scripted","repo":"SonyCSLParis/ssl-singer-identity","repo_kind":"official","path":"singer_identity/utils/fetch_pretrained.py","file_url":"https://github.com/SonyCSLParis/ssl-singer-identity/blob/HEAD/singer_identity/utils/fetch_pretrained.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":"df84f474cafaa6b7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}