{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FFVLLEDMCNREIMWXUJ6E3ERIRS","short_pith_number":"pith:FFVLLEDM","schema_version":"1.0","canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","source":{"kind":"arxiv","id":"2204.03939","version":2},"attestation_state":"computed","paper":{"title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhao, Chutong Meng, Jun Cao, Mingxuan Wang, Rong Ye, Tao Wang, Tom Ko","submitted_at":"2022-04-08T08:59:33Z","abstract_excerpt":"This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. We create the corpus by translating the text in GigaSpeech, an English ASR corpus, into German and Chinese. The training set is translated by a strong machine translation system and the test set is translated by human. ST models trained with an addition of our corpus obtain new state-of-the-art results on the MuST-C English-German benchmark test set. We provide a detailed description of the translation process and verify its quality. We make the translated text data public and hope to facilitate research in spee"},"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":"2204.03939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T08:59:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ff14160778ad73dd1f0d386a976ea73621e640a86f8cbe004c0b20e66a3391d2","abstract_canon_sha256":"66ebeded9a736316142317a3b838fb4dfb68e1c53c93cd6b7fbaf909a387c4e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:37.175196Z","signature_b64":"qm4nhq+DSKxDUwQv3mZzBBhy0rXPM8MC566JzcUTblHih0xL5LNriGlZP+QsQKqQZ7h7WZ/C6SLbKUpMxk7xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","last_reissued_at":"2026-07-05T06:17:37.174789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:37.174789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhao, Chutong Meng, Jun Cao, Mingxuan Wang, Rong Ye, Tao Wang, Tom Ko","submitted_at":"2022-04-08T08:59:33Z","abstract_excerpt":"This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. We create the corpus by translating the text in GigaSpeech, an English ASR corpus, into German and Chinese. The training set is translated by a strong machine translation system and the test set is translated by human. ST models trained with an addition of our corpus obtain new state-of-the-art results on the MuST-C English-German benchmark test set. We provide a detailed description of the translation process and verify its quality. We make the translated text data public and hope to facilitate research in spee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03939","kind":"arxiv","version":2},"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/2204.03939/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":"2204.03939","created_at":"2026-07-05T06:17:37.174846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03939v2","created_at":"2026-07-05T06:17:37.174846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03939","created_at":"2026-07-05T06:17:37.174846+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFVLLEDMCNRE","created_at":"2026-07-05T06:17:37.174846+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFVLLEDMCNREIMWX","created_at":"2026-07-05T06:17:37.174846+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFVLLEDM","created_at":"2026-07-05T06:17:37.174846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17435","citing_title":"MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS","json":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS.json","graph_json":"https://pith.science/api/pith-number/FFVLLEDMCNREIMWXUJ6E3ERIRS/graph.json","events_json":"https://pith.science/api/pith-number/FFVLLEDMCNREIMWXUJ6E3ERIRS/events.json","paper":"https://pith.science/paper/FFVLLEDM"},"agent_actions":{"view_html":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS","download_json":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS.json","view_paper":"https://pith.science/paper/FFVLLEDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03939&json=true","fetch_graph":"https://pith.science/api/pith-number/FFVLLEDMCNREIMWXUJ6E3ERIRS/graph.json","fetch_events":"https://pith.science/api/pith-number/FFVLLEDMCNREIMWXUJ6E3ERIRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/action/storage_attestation","attest_author":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/action/author_attestation","sign_citation":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/action/citation_signature","submit_replication":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/action/replication_record"}},"created_at":"2026-07-05T06:17:37.174846+00:00","updated_at":"2026-07-05T06:17:37.174846+00:00"}