{"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/voxsim-a-perceptual-voice-similarity-dataset","title":"VoxSim: A perceptual voice similarity dataset","arxiv_id":"2407.18505","date":"2024-07-26","proceeding":null,"authors":["Junseok Ahn","Youkyum Kim","Yeunju Choi","Doyeop Kwak","Ji-Hoon Kim","Seongkyu Mun","Joon Son Chung"],"abstract":"This paper introduces VoxSim, a dataset of perceptual voice similarity ratings. Recent efforts to automate the assessment of speech synthesis technologies have primarily focused on predicting mean opinion score of naturalness, leaving speaker voice similarity relatively unexplored due to a lack of extensive training data. To address this, we generate about 41k utterance pairs from the VoxCeleb dataset, a widely utilised speech dataset for speaker recognition, and collect nearly 70k speaker similarity scores through a listening test. VoxSim offers a valuable resource for the development and benchmarking of speaker similarity prediction models. We provide baseline results of speaker similarity prediction models on the VoxSim test set and further demonstrate that the model trained on our dataset generalises to the out-of-domain VCC2018 dataset.","url_abs":"https://arxiv.org/abs/2407.18505v1","url_pdf":"https://arxiv.org/pdf/2407.18505v1.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":"voxsim-a-perceptual-voice-similarity-dataset","repo_url":"https://github.com/kaistmm/voxsim_trainer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"speaker-recognition","task_name":"Speaker Recognition"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"voice-similarity","task_name":"Voice Similarity"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[{"slug":"voxsim","name":"VoxSim","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.18505","atlas_url":"https://app.syntology.ai/?focus=2407.18505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18505"}},"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/kaistmm/voxsim_trainer","reach":{"status":"ok"}}],"summary":{"ran":9,"ran_draft_wrong":3,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":14,"ran":13,"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":14,"samples":[{"code_sha256_prefix":"2f8f70723c6fc25c","entry":"ComputeErrorRates","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"tuneThreshold.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/tuneThreshold.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f8f70723c6fc25c"}},{"code_sha256_prefix":"2e9b31102cfe118e","entry":"ComputeMinDcf","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"tuneThreshold.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/tuneThreshold.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2e9b31102cfe118e"}},{"code_sha256_prefix":"8857cf22d4733067","entry":"Optimizer","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"optimizer/adam.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/optimizer/adam.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8857cf22d4733067"}},{"code_sha256_prefix":"25b50b526d156bc2","entry":"act_fun","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"models/sincnet.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/models/sincnet.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25b50b526d156bc2"}},{"code_sha256_prefix":"9e363845f139a627","entry":"find_option_type","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"trainSpeakerNet.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/trainSpeakerNet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e363845f139a627"}},{"code_sha256_prefix":"b380f42b5b71cc47","entry":"flip","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"models/sincnet.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/models/sincnet.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b380f42b5b71cc47"}},{"code_sha256_prefix":"1236c5af96d325a8","entry":"is_within_directory","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"dataprep.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/dataprep.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1236c5af96d325a8"}},{"code_sha256_prefix":"77c379958bd0a3ed","entry":"md5","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"dataprep.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/dataprep.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77c379958bd0a3ed"}},{"code_sha256_prefix":"e42001624ddd039a","entry":"round_down","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"DatasetLoader.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/DatasetLoader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e42001624ddd039a"}},{"code_sha256_prefix":"e853a80fddd327a4","entry":"score2class2","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e853a80fddd327a4"}},{"code_sha256_prefix":"d0d6e2ef34d8b563","entry":"score2class4","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d0d6e2ef34d8b563"}},{"code_sha256_prefix":"a64e85f20d5e56b8","entry":"sinc","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"models/sincnet.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/models/sincnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a64e85f20d5e56b8"}},{"code_sha256_prefix":"5ba0d1f2b1bd474b","entry":"tuneThresholdfromScore","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"tuneThreshold.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/tuneThreshold.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5ba0d1f2b1bd474b"}},{"code_sha256_prefix":"4d3faaaa1c706b0b","entry":"accuracy","repo":"kaistmm/voxsim_trainer","repo_kind":"official","path":"utils.py","file_url":"https://github.com/kaistmm/voxsim_trainer/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d3faaaa1c706b0b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}