{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6JZXRR2VEIJ4KONCOPTRUWN65U","short_pith_number":"pith:6JZXRR2V","schema_version":"1.0","canonical_sha256":"f27378c7552213c539a273e71a59beed07051e5c3638e2dc959ecdcb1f488239","source":{"kind":"arxiv","id":"2011.12998","version":1},"attestation_state":"computed","paper":{"title":"VoxLingua107: a Dataset for Spoken Language Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"J\\\"orgen Valk, Tanel Alum\\\"ae","submitted_at":"2020-11-25T19:47:38Z","abstract_excerpt":"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 th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.12998","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-25T19:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"634b052208629f65258f47d22be69a69962d2aa2f66def01659e77da8d93bc44","abstract_canon_sha256":"634d4fcc58990784541fe78e04a3214d87f904e4f17f6db16691d175d1e8dcd0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:49.858697Z","signature_b64":"1SeElkeBIElv0AAsGE22gsa6G4gcVZ1kWvWK7YOsvmPeCLv8yb0TC0h8Ht8h550Wwd/cXvDEtXPGD3l6AzPRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f27378c7552213c539a273e71a59beed07051e5c3638e2dc959ecdcb1f488239","last_reissued_at":"2026-07-05T01:54:49.858279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:49.858279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoxLingua107: a Dataset for Spoken Language Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"J\\\"orgen Valk, Tanel Alum\\\"ae","submitted_at":"2020-11-25T19:47:38Z","abstract_excerpt":"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 th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12998","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.12998/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.12998","created_at":"2026-07-05T01:54:49.858341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.12998v1","created_at":"2026-07-05T01:54:49.858341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12998","created_at":"2026-07-05T01:54:49.858341+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JZXRR2VEIJ4","created_at":"2026-07-05T01:54:49.858341+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JZXRR2VEIJ4KONC","created_at":"2026-07-05T01:54:49.858341+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JZXRR2V","created_at":"2026-07-05T01:54:49.858341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18436","citing_title":"Voice of a Continent: Mapping Africa's Speech Technology Frontier","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U","json":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U.json","graph_json":"https://pith.science/api/pith-number/6JZXRR2VEIJ4KONCOPTRUWN65U/graph.json","events_json":"https://pith.science/api/pith-number/6JZXRR2VEIJ4KONCOPTRUWN65U/events.json","paper":"https://pith.science/paper/6JZXRR2V"},"agent_actions":{"view_html":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U","download_json":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U.json","view_paper":"https://pith.science/paper/6JZXRR2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.12998&json=true","fetch_graph":"https://pith.science/api/pith-number/6JZXRR2VEIJ4KONCOPTRUWN65U/graph.json","fetch_events":"https://pith.science/api/pith-number/6JZXRR2VEIJ4KONCOPTRUWN65U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U/action/storage_attestation","attest_author":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U/action/author_attestation","sign_citation":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U/action/citation_signature","submit_replication":"https://pith.science/pith/6JZXRR2VEIJ4KONCOPTRUWN65U/action/replication_record"}},"created_at":"2026-07-05T01:54:49.858341+00:00","updated_at":"2026-07-05T01:54:49.858341+00:00"}