{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SWFU5QAXZ35SI47HVWYOHLQX4I","short_pith_number":"pith:SWFU5QAX","schema_version":"1.0","canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","source":{"kind":"arxiv","id":"1903.00216","version":1},"attestation_state":"computed","paper":{"title":"KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cornelius Weber, Egor Lakomkin, Stefan Wermter, Sven Magg","submitted_at":"2019-03-01T09:14:50Z","abstract_excerpt":"In this paper, we describe KT-Speech-Crawler: an approach for automatic dataset construction for speech recognition by crawling YouTube videos. We outline several filtering and post-processing steps, which extract samples that can be used for training end-to-end neural speech recognition systems. In our experiments, we demonstrate that a single-core version of the crawler can obtain around 150 hours of transcribed speech within a day, containing an estimated 3.5% word error rate in the transcriptions. Automatically collected samples contain reading and spontaneous speech recorded in various co"},"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":"1903.00216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T09:14:50Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"539ae64612d90bdfb350d9084e2177d92152e1e15139dc6a0ff5b21738e5c047","abstract_canon_sha256":"ccfc523a0857220cf5237d7dd3d3fd369a7b483c094142a4650a4c8e628860f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:20.502590Z","signature_b64":"VOc9YBlYZ/9hwbgZVy5AzeSlXliVLwr2tcpkL3Vw/9pWgRBc5GHwzc8dzCzqV1X2uougSLeCIOZFRQArVx5MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"958b4ec017cefb2473e7adb0e3ae17e212a46d0c06396f9d4e30cbcbedc9cf7c","last_reissued_at":"2026-05-17T23:52:20.501891Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:20.501891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cornelius Weber, Egor Lakomkin, Stefan Wermter, Sven Magg","submitted_at":"2019-03-01T09:14:50Z","abstract_excerpt":"In this paper, we describe KT-Speech-Crawler: an approach for automatic dataset construction for speech recognition by crawling YouTube videos. We outline several filtering and post-processing steps, which extract samples that can be used for training end-to-end neural speech recognition systems. In our experiments, we demonstrate that a single-core version of the crawler can obtain around 150 hours of transcribed speech within a day, containing an estimated 3.5% word error rate in the transcriptions. Automatically collected samples contain reading and spontaneous speech recorded in various co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00216","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":""},"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":"1903.00216","created_at":"2026-05-17T23:52:20.502016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00216v1","created_at":"2026-05-17T23:52:20.502016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00216","created_at":"2026-05-17T23:52:20.502016+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWFU5QAXZ35S","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWFU5QAXZ35SI47H","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWFU5QAX","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I","json":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I.json","graph_json":"https://pith.science/api/pith-number/SWFU5QAXZ35SI47HVWYOHLQX4I/graph.json","events_json":"https://pith.science/api/pith-number/SWFU5QAXZ35SI47HVWYOHLQX4I/events.json","paper":"https://pith.science/paper/SWFU5QAX"},"agent_actions":{"view_html":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I","download_json":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I.json","view_paper":"https://pith.science/paper/SWFU5QAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00216&json=true","fetch_graph":"https://pith.science/api/pith-number/SWFU5QAXZ35SI47HVWYOHLQX4I/graph.json","fetch_events":"https://pith.science/api/pith-number/SWFU5QAXZ35SI47HVWYOHLQX4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/action/storage_attestation","attest_author":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/action/author_attestation","sign_citation":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/action/citation_signature","submit_replication":"https://pith.science/pith/SWFU5QAXZ35SI47HVWYOHLQX4I/action/replication_record"}},"created_at":"2026-05-17T23:52:20.502016+00:00","updated_at":"2026-05-17T23:52:20.502016+00:00"}