{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L3FPEJY5PIGNA6WVPDML4GGSCM","short_pith_number":"pith:L3FPEJY5","schema_version":"1.0","canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","source":{"kind":"arxiv","id":"2211.04508","version":1},"attestation_state":"computed","paper":{"title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Beno\\^it Sagot, Changhan Wang, Holger Schwenk, Hongyu Gong, Jingfei Du, Juan Pino, Ning Dong, Paul-Ambroise Duquenne, Vedanuj Goswani","submitted_at":"2022-11-08T19:09:27Z","abstract_excerpt":"We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by fe"},"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":"2211.04508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-08T19:09:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4877502f1f2fb88f2a539d1299cddec3a79e253080cfde53e01b96a8bb78ed8f","abstract_canon_sha256":"463ad0f61ff88f2bbb14f17ecbe57311753adf43290ce372228027e1ca859993"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:38.709767Z","signature_b64":"BABVf8/i84WbFhM3IioEwpyeE0/iCjZB3/5kyZ2huIFy6qzuU0G2TmG8ypJfpMxYU6xAgHprJgRIoRYg1uA1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ecaf2271d7a0cd07ad578d8be18d2131d78f6993286ae5333aab10cebdc5218","last_reissued_at":"2026-07-05T05:14:38.709251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:38.709251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechMatrix: A Large-Scale Mined Corpus of Multilingual Speech-to-Speech Translations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ann Lee, Beno\\^it Sagot, Changhan Wang, Holger Schwenk, Hongyu Gong, Jingfei Du, Juan Pino, Ning Dong, Paul-Ambroise Duquenne, Vedanuj Goswani","submitted_at":"2022-11-08T19:09:27Z","abstract_excerpt":"We present SpeechMatrix, a large-scale multilingual corpus of speech-to-speech translations mined from real speech of European Parliament recordings. It contains speech alignments in 136 language pairs with a total of 418 thousand hours of speech. To evaluate the quality of this parallel speech, we train bilingual speech-to-speech translation models on mined data only and establish extensive baseline results on EuroParl-ST, VoxPopuli and FLEURS test sets. Enabled by the multilinguality of SpeechMatrix, we also explore multilingual speech-to-speech translation, a topic which was addressed by fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04508","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.04508/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":"2211.04508","created_at":"2026-07-05T05:14:38.709324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.04508v1","created_at":"2026-07-05T05:14:38.709324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04508","created_at":"2026-07-05T05:14:38.709324+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3FPEJY5PIGN","created_at":"2026-07-05T05:14:38.709324+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3FPEJY5PIGNA6WV","created_at":"2026-07-05T05:14:38.709324+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3FPEJY5","created_at":"2026-07-05T05:14:38.709324+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/L3FPEJY5PIGNA6WVPDML4GGSCM","json":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM.json","graph_json":"https://pith.science/api/pith-number/L3FPEJY5PIGNA6WVPDML4GGSCM/graph.json","events_json":"https://pith.science/api/pith-number/L3FPEJY5PIGNA6WVPDML4GGSCM/events.json","paper":"https://pith.science/paper/L3FPEJY5"},"agent_actions":{"view_html":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM","download_json":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM.json","view_paper":"https://pith.science/paper/L3FPEJY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.04508&json=true","fetch_graph":"https://pith.science/api/pith-number/L3FPEJY5PIGNA6WVPDML4GGSCM/graph.json","fetch_events":"https://pith.science/api/pith-number/L3FPEJY5PIGNA6WVPDML4GGSCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/action/storage_attestation","attest_author":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/action/author_attestation","sign_citation":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/action/citation_signature","submit_replication":"https://pith.science/pith/L3FPEJY5PIGNA6WVPDML4GGSCM/action/replication_record"}},"created_at":"2026-07-05T05:14:38.709324+00:00","updated_at":"2026-07-05T05:14:38.709324+00:00"}