{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TDXW245D3F2WHMC2ONAMTWRJM5","short_pith_number":"pith:TDXW245D","schema_version":"1.0","canonical_sha256":"98ef6d73a3d97563b05a7340c9da2967707c2b373acf163fa0a7eab4c709753e","source":{"kind":"arxiv","id":"2306.01327","version":1},"attestation_state":"computed","paper":{"title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gerard I. G\\'allego, Ioannis Tsiamas, Jos\\'e A. R. Fonollosa, Marta R. Costa-juss\\`a","submitted_at":"2023-06-02T07:48:37Z","abstract_excerpt":"This paper describes the submission of the UPC Machine Translation group to the IWSLT 2023 Offline Speech Translation task. Our Speech Translation systems utilize foundation models for speech (wav2vec 2.0) and text (mBART50). We incorporate a Siamese pretraining step of the speech and text encoders with CTC and Optimal Transport, to adapt the speech representations to the space of the text model, thus maximizing transfer learning from MT. After this pretraining, we fine-tune our system end-to-end on ST, with Cross Entropy and Knowledge Distillation. Apart from the available ST corpora, we crea"},"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":"2306.01327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T07:48:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"62fecb808a2b23371cb77bf82072d22883ca9e9a69d2931e17e4aa1fa803d6e4","abstract_canon_sha256":"378de6bc6bb957528692084f513e69c600b547c565c3d7d311ec16f353fa26c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:52.612762Z","signature_b64":"xbhx7X/reRWqhcI7RpvFOqP80QI8XbrU+Vgjk9xqLaKzx4TQLzM/RrV/5kItbS9EgLyZ3AdQBaa1YC5R8ZapAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ef6d73a3d97563b05a7340c9da2967707c2b373acf163fa0a7eab4c709753e","last_reissued_at":"2026-07-05T06:16:52.612428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:52.612428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Translation with Foundation Models and Optimal Transport: UPC at IWSLT23","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gerard I. G\\'allego, Ioannis Tsiamas, Jos\\'e A. R. Fonollosa, Marta R. Costa-juss\\`a","submitted_at":"2023-06-02T07:48:37Z","abstract_excerpt":"This paper describes the submission of the UPC Machine Translation group to the IWSLT 2023 Offline Speech Translation task. Our Speech Translation systems utilize foundation models for speech (wav2vec 2.0) and text (mBART50). We incorporate a Siamese pretraining step of the speech and text encoders with CTC and Optimal Transport, to adapt the speech representations to the space of the text model, thus maximizing transfer learning from MT. After this pretraining, we fine-tune our system end-to-end on ST, with Cross Entropy and Knowledge Distillation. Apart from the available ST corpora, we crea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01327","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/2306.01327/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":"2306.01327","created_at":"2026-07-05T06:16:52.612483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01327v1","created_at":"2026-07-05T06:16:52.612483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01327","created_at":"2026-07-05T06:16:52.612483+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDXW245D3F2W","created_at":"2026-07-05T06:16:52.612483+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDXW245D3F2WHMC2","created_at":"2026-07-05T06:16:52.612483+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDXW245D","created_at":"2026-07-05T06:16:52.612483+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/TDXW245D3F2WHMC2ONAMTWRJM5","json":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5.json","graph_json":"https://pith.science/api/pith-number/TDXW245D3F2WHMC2ONAMTWRJM5/graph.json","events_json":"https://pith.science/api/pith-number/TDXW245D3F2WHMC2ONAMTWRJM5/events.json","paper":"https://pith.science/paper/TDXW245D"},"agent_actions":{"view_html":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5","download_json":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5.json","view_paper":"https://pith.science/paper/TDXW245D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01327&json=true","fetch_graph":"https://pith.science/api/pith-number/TDXW245D3F2WHMC2ONAMTWRJM5/graph.json","fetch_events":"https://pith.science/api/pith-number/TDXW245D3F2WHMC2ONAMTWRJM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5/action/storage_attestation","attest_author":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5/action/author_attestation","sign_citation":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5/action/citation_signature","submit_replication":"https://pith.science/pith/TDXW245D3F2WHMC2ONAMTWRJM5/action/replication_record"}},"created_at":"2026-07-05T06:16:52.612483+00:00","updated_at":"2026-07-05T06:16:52.612483+00:00"}