{"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/voxlingua107-a-dataset-for-spoken-language-1","title":"VoxLingua107: a Dataset for Spoken Language Recognition","arxiv_id":"2011.12998","date":"2020-11-25","proceeding":null,"authors":["Jörgen Valk","Tanel Alumäe"],"abstract":"This paper investigates the use of automatically collected web audio data for the task of spoken language recognition. We generate semi-random search phrases from language-specific Wikipedia data that are then used to retrieve videos from YouTube for 107 languages. Speech activity detection and speaker diarization are used to extract segments from the videos that contain speech. Post-filtering is used to remove segments from the database that are likely not in the given language, increasing the proportion of correctly labeled segments to 98%, based on crowd-sourced verification. The size of the resulting training set (VoxLingua107) is 6628 hours (62 hours per language on the average) and it is accompanied by an evaluation set of 1609 verified utterances. We use the data to build language recognition models for several spoken language identification tasks. Experiments show that using the automatically retrieved training data gives competitive results to using hand-labeled proprietary datasets. The dataset is publicly available.","url_abs":"https://arxiv.org/abs/2011.12998v1","url_pdf":"https://arxiv.org/pdf/2011.12998v1.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":"voxlingua107-a-dataset-for-spoken-language-1","repo_url":"https://github.com/alumae/torch-xvectors-wav","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"voxlingua107-a-dataset-for-spoken-language-1","repo_url":"https://github.com/rush-d/spoken-language-identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"action-detection","task_name":"Action Detection"},{"task_slug":"activity-detection","task_name":"Activity Detection"},{"task_slug":"language-identification","task_name":"Language Identification"},{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"spoken-language-identification","task_name":"Spoken language identification"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"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/rush-d/spoken-language-identification","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alumae/torch-xvectors-wav","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"97de2d15419714bf","entry":"lsoft_loss","repo":"alumae/torch-xvectors-wav","repo_kind":"official","path":"models.py","file_url":"https://github.com/alumae/torch-xvectors-wav/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97de2d15419714bf"}},{"code_sha256_prefix":"1419cf42ba28ab11","entry":"max_outlier_loss","repo":"alumae/torch-xvectors-wav","repo_kind":"official","path":"models.py","file_url":"https://github.com/alumae/torch-xvectors-wav/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1419cf42ba28ab11"}},{"code_sha256_prefix":"d4b5a745f79d0f17","entry":"nll_loss_with_label_smoothing","repo":"alumae/torch-xvectors-wav","repo_kind":"official","path":"models.py","file_url":"https://github.com/alumae/torch-xvectors-wav/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d4b5a745f79d0f17"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}