{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6F4W3PUCECMKK3EG5QTEVBRYEY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9e5124050d64c8f90f8bc6169e51ebce39fb96c84a1ff446c4a5657873cac27d","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-17T05:09:44Z","title_canon_sha256":"48e8f11f5e1d5e1d08ad83591fe2118878988b9d7923bce041897613d97a1238"},"schema_version":"1.0","source":{"id":"2112.09323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.09323","created_at":"2026-07-05T03:41:45Z"},{"alias_kind":"arxiv_version","alias_value":"2112.09323v1","created_at":"2026-07-05T03:41:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.09323","created_at":"2026-07-05T03:41:45Z"},{"alias_kind":"pith_short_12","alias_value":"6F4W3PUCECMK","created_at":"2026-07-05T03:41:45Z"},{"alias_kind":"pith_short_16","alias_value":"6F4W3PUCECMKK3EG","created_at":"2026-07-05T03:41:45Z"},{"alias_kind":"pith_short_8","alias_value":"6F4W3PUC","created_at":"2026-07-05T03:41:45Z"}],"graph_snapshots":[{"event_id":"sha256:d463508e282de0d25f82bc266739ff6bee3d37826677ab0a05685edbff129556","target":"graph","created_at":"2026-07-05T03:41:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.09323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we construct a new Japanese speech corpus called \"JTubeSpeech.\" Although recent end-to-end learning requires large-size speech corpora, open-sourced such corpora for languages other than English have not yet been established. In this paper, we describe the construction of a corpus from YouTube videos and subtitles for speech recognition and speaker verification. Our method can automatically filter the videos and subtitles with almost no language-dependent processes. We consistently employ Connectionist Temporal Classification (CTC)-based techniques for automatic speech recogniti","authors_text":"Ludwig K\\\"urzinger, Sayaka Shiota, Shinji Watanabe, Shinnosuke Takamichi, Takaaki Saeki","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-17T05:09:44Z","title":"JTubeSpeech: corpus of Japanese speech collected from YouTube for speech recognition and speaker verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.09323","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:367a4a03ced4316977e689304abf605595f1eb430cd6a19324f731f7674f250b","target":"record","created_at":"2026-07-05T03:41:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9e5124050d64c8f90f8bc6169e51ebce39fb96c84a1ff446c4a5657873cac27d","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-17T05:09:44Z","title_canon_sha256":"48e8f11f5e1d5e1d08ad83591fe2118878988b9d7923bce041897613d97a1238"},"schema_version":"1.0","source":{"id":"2112.09323","kind":"arxiv","version":1}},"canonical_sha256":"f1796dbe822098a56c86ec264a86382611619f1832f502e511d7852c3b97991c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1796dbe822098a56c86ec264a86382611619f1832f502e511d7852c3b97991c","first_computed_at":"2026-07-05T03:41:45.103367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:45.103367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dHm0C9vecdKaugnQqdLO+C9KXourmeO03XxzLlzh3EV3e0kxk/mKEHqVnmgb12PDaj9ioBCARvgIlNkMIyi3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:45.103709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.09323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:367a4a03ced4316977e689304abf605595f1eb430cd6a19324f731f7674f250b","sha256:d463508e282de0d25f82bc266739ff6bee3d37826677ab0a05685edbff129556"],"state_sha256":"9d13d685f4df0fbca9dd7ffaf2ee29e4e34d41edbbea3ebde49b613fa84b0079"}