{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/voice-similarity","name":"Voice Similarity","slug":"voice-similarity","description_markdown":null,"categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":14,"papers_with_code":5,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":14,"of":14,"of_with_code":5,"tagged_in_all":14,"counts":{"archive_papers_tagged":14,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":14,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/yourtts-towards-zero-shot-multi-speaker-tts","slug":"yourtts-towards-zero-shot-multi-speaker-tts","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","date":"2021-12-04","arxiv_id":"2112.02418","repositories_listed":3,"syntology":null},{"url":"/paper/speech-pseudonymisation-assessment-using","slug":"speech-pseudonymisation-assessment-using","title":"Speech Pseudonymisation Assessment Using Voice Similarity Matrices","date":"2020-08-30","arxiv_id":"2008.13144","repositories_listed":2,"syntology":null},{"url":"/paper/voxsim-a-perceptual-voice-similarity-dataset","slug":"voxsim-a-perceptual-voice-similarity-dataset","title":"VoxSim: A perceptual voice similarity dataset","date":"2024-07-26","arxiv_id":"2407.18505","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/voxsim-a-perceptual-voice-similarity-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.18505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18505"}},"official":{"repos":["kaistmm/voxsim_trainer"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/singer-identity-representation-learning-using-1","slug":"singer-identity-representation-learning-using-1","title":"Singer Identity Representation Learning using Self-Supervised Techniques","date":"2024-01-10","arxiv_id":"2401.05064","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/singer-identity-representation-learning-using-1#ran","syntology_url":"https://syntology.ai/paper/2401.05064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05064"}},"official":{"repos":["SonyCSLParis/ssl-singer-identity"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/svsnet-an-end-to-end-speaker-voice-similarity","slug":"svsnet-an-end-to-end-speaker-voice-similarity","title":"SVSNet: An End-to-end Speaker Voice Similarity Assessment Model","date":"2021-07-20","arxiv_id":"2107.09392","repositories_listed":1,"syntology":null},{"url":null,"slug":"aligndit-multimodal-aligned-diffusion","title":"AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation","date":"2025-04-29","arxiv_id":"2504.20629","repositories_listed":0,"syntology":null},{"url":null,"slug":"dmdspeech-distilled-diffusion-model","title":"DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis","date":"2024-10-14","arxiv_id":"2410.11097","repositories_listed":0,"syntology":null},{"url":null,"slug":"disentangling-segmental-and-prosodic-factors","title":"Disentangling segmental and prosodic factors to non-native speech comprehensibility","date":"2024-08-20","arxiv_id":"2408.10997","repositories_listed":0,"syntology":null},{"url":null,"slug":"svsnet-enhancing-speaker-voice-similarity","title":"SVSNet+: Enhancing Speaker Voice Similarity Assessment Models with Representations from Speech Foundation Models","date":"2024-06-12","arxiv_id":"2406.08445","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffsvc-a-diffusion-probabilistic-model-for","title":"DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversion","date":"2021-05-28","arxiv_id":"2105.13871","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adaptive-learning-based-generative","title":"An Adaptive Learning based Generative Adversarial Network for One-To-One Voice Conversion","date":"2021-04-25","arxiv_id":"2104.12159","repositories_listed":0,"syntology":null},{"url":null,"slug":"ppg-based-singing-voice-conversion-with","title":"PPG-based singing voice conversion with adversarial representation learning","date":"2020-10-28","arxiv_id":"2010.14804","repositories_listed":0,"syntology":null},{"url":null,"slug":"waveform-generation-for-text-to-speech","title":"Waveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks","date":"2018-10-30","arxiv_id":"1810.12598","repositories_listed":0,"syntology":null},{"url":null,"slug":"sample-efficient-adaptive-text-to-speech","title":"Sample Efficient Adaptive Text-to-Speech","date":"2018-09-27","arxiv_id":"1809.10460","repositories_listed":0,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/task/voice-similarity/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/voice-similarity/papers/ran/1","json":"/task/voice-similarity/papers/ran/1.json","rows":2}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"badf7e831d5d259d2692e64b9bddd5f166fae1cd65a94a031a5cfaf5db8efee1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}