{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VM3PATYP6CQEA7QIR25G7MSWC4","short_pith_number":"pith:VM3PATYP","schema_version":"1.0","canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","source":{"kind":"arxiv","id":"2206.13756","version":2},"attestation_state":"computed","paper":{"title":"On the Impact of Noises in Crowd-Sourced Data for Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","submitted_at":"2022-06-28T05:01:06Z","abstract_excerpt":"Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight translation directions. This dataset passes several quality-control filters during creation. However, we find that MuST-C still suffers from three major quality issues: audio-text misalignment, inaccurate translation, and unnecessary speaker's name. What are the impacts of these data quality issues for model development and evaluation? In this paper, we propose an a"},"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":"2206.13756","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T05:01:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a9a423e90f841c75b2b691a9556dc7b68e2f8c41bebacdc128e55bb38248604","abstract_canon_sha256":"97b23d22f97ccd688eee3a569eb9f4d110121f6e3be03eb330b19a5848cd8727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:37.447845Z","signature_b64":"FnwEwtxRMUMvk058OHzVr2i6pTGO8VTU/gBe6gj4TCkLGcfYTbR2m7nE10gLCmZHyjzmnqJVQtLmwItjfajbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","last_reissued_at":"2026-07-05T04:36:37.447409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:37.447409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Impact of Noises in Crowd-Sourced Data for Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","submitted_at":"2022-06-28T05:01:06Z","abstract_excerpt":"Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight translation directions. This dataset passes several quality-control filters during creation. However, we find that MuST-C still suffers from three major quality issues: audio-text misalignment, inaccurate translation, and unnecessary speaker's name. What are the impacts of these data quality issues for model development and evaluation? In this paper, we propose an a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13756","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/2206.13756/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":"2206.13756","created_at":"2026-07-05T04:36:37.447471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.13756v2","created_at":"2026-07-05T04:36:37.447471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13756","created_at":"2026-07-05T04:36:37.447471+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM3PATYP6CQE","created_at":"2026-07-05T04:36:37.447471+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM3PATYP6CQEA7QI","created_at":"2026-07-05T04:36:37.447471+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM3PATYP","created_at":"2026-07-05T04:36:37.447471+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/VM3PATYP6CQEA7QIR25G7MSWC4","json":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4.json","graph_json":"https://pith.science/api/pith-number/VM3PATYP6CQEA7QIR25G7MSWC4/graph.json","events_json":"https://pith.science/api/pith-number/VM3PATYP6CQEA7QIR25G7MSWC4/events.json","paper":"https://pith.science/paper/VM3PATYP"},"agent_actions":{"view_html":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4","download_json":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4.json","view_paper":"https://pith.science/paper/VM3PATYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.13756&json=true","fetch_graph":"https://pith.science/api/pith-number/VM3PATYP6CQEA7QIR25G7MSWC4/graph.json","fetch_events":"https://pith.science/api/pith-number/VM3PATYP6CQEA7QIR25G7MSWC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/action/storage_attestation","attest_author":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/action/author_attestation","sign_citation":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/action/citation_signature","submit_replication":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/action/replication_record"}},"created_at":"2026-07-05T04:36:37.447471+00:00","updated_at":"2026-07-05T04:36:37.447471+00:00"}