{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3QVLLIJV3NB3CTYIVME6XC64PR","short_pith_number":"pith:3QVLLIJV","schema_version":"1.0","canonical_sha256":"dc2ab5a135db43b14f08ab09eb8bdc7c458cd76260c470ecd84b114ce16ad98d","source":{"kind":"arxiv","id":"2201.03713","version":3},"attestation_state":"computed","paper":{"title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Heiga Zen, Michelle Tadmor Ramanovich, Quan Wang, Ye Jia","submitted_at":"2022-01-11T00:27:08Z","abstract_excerpt":"We introduce CVSS, a massively multilingual-to-English speech-to-speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the Common Voice speech corpus and the CoVoST 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems. Two versions of translation speeches are provided: 1) CVSS-C: All the translation speeches are in a single high-quality canonical voice; 2) CVSS-T: The translation speeches are in voices transferred from the correspon"},"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":"2201.03713","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-11T00:27:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"0d3c641daf8b896cf99b9c061bdfa7962068e808d6d7a0823f7d644ba23c7163","abstract_canon_sha256":"43d9c0c6a4694317f30b7d92d32d04581fd6a4c42923e7e6b90f102ec24856d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:49.665897Z","signature_b64":"NizIgAKEKBOSiOLLMPnv09cl3iDb0KczycQigr0kZEWNnDtiRB95PtvUWj6tV0CbPG4b7zC2dgYp1ORFbSdKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2ab5a135db43b14f08ab09eb8bdc7c458cd76260c470ecd84b114ce16ad98d","last_reissued_at":"2026-07-05T04:34:49.665411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:49.665411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Heiga Zen, Michelle Tadmor Ramanovich, Quan Wang, Ye Jia","submitted_at":"2022-01-11T00:27:08Z","abstract_excerpt":"We introduce CVSS, a massively multilingual-to-English speech-to-speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the Common Voice speech corpus and the CoVoST 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems. Two versions of translation speeches are provided: 1) CVSS-C: All the translation speeches are in a single high-quality canonical voice; 2) CVSS-T: The translation speeches are in voices transferred from the correspon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.03713","kind":"arxiv","version":3},"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/2201.03713/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":"2201.03713","created_at":"2026-07-05T04:34:49.665472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.03713v3","created_at":"2026-07-05T04:34:49.665472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.03713","created_at":"2026-07-05T04:34:49.665472+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QVLLIJV3NB3","created_at":"2026-07-05T04:34:49.665472+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QVLLIJV3NB3CTYI","created_at":"2026-07-05T04:34:49.665472+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QVLLIJV","created_at":"2026-07-05T04:34:49.665472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13121","citing_title":"NaturalFlow: Reducing Disruptive Pauses for Natural Speech Flow in Simultaneous Speech-to-Speech Translation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR","json":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR.json","graph_json":"https://pith.science/api/pith-number/3QVLLIJV3NB3CTYIVME6XC64PR/graph.json","events_json":"https://pith.science/api/pith-number/3QVLLIJV3NB3CTYIVME6XC64PR/events.json","paper":"https://pith.science/paper/3QVLLIJV"},"agent_actions":{"view_html":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR","download_json":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR.json","view_paper":"https://pith.science/paper/3QVLLIJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.03713&json=true","fetch_graph":"https://pith.science/api/pith-number/3QVLLIJV3NB3CTYIVME6XC64PR/graph.json","fetch_events":"https://pith.science/api/pith-number/3QVLLIJV3NB3CTYIVME6XC64PR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR/action/storage_attestation","attest_author":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR/action/author_attestation","sign_citation":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR/action/citation_signature","submit_replication":"https://pith.science/pith/3QVLLIJV3NB3CTYIVME6XC64PR/action/replication_record"}},"created_at":"2026-07-05T04:34:49.665472+00:00","updated_at":"2026-07-05T04:34:49.665472+00:00"}