{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LOV344YSF2VGCACK3KGE2Y5XEJ","short_pith_number":"pith:LOV344YS","schema_version":"1.0","canonical_sha256":"5babbe73122eaa61004ada8c4d63b7227233143002f660465777ff79f4106f07","source":{"kind":"arxiv","id":"2212.09359","version":3},"attestation_state":"computed","paper":{"title":"WACO: Word-Aligned Contrastive Learning for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","submitted_at":"2022-12-19T10:49:35Z","abstract_excerpt":"End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model's performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. "},"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":"2212.09359","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T10:49:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"430c0e4bee78523a1d7c4d22f7967d88127800ee1c235758f00e93549d1854fe","abstract_canon_sha256":"ccd0b2ac10220ae212c2f0047d98f80fa99eca4f99a6e857065328d6c42c0ec3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:33.166793Z","signature_b64":"o15NHTNoHrU667w8dUCG8Ws8ApBjF02sWKL/EhF7bAcDWmuWvwePXgy/TkZ2+nZYHX1Z6SejHjqwx6aDXQ6/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5babbe73122eaa61004ada8c4d63b7227233143002f660465777ff79f4106f07","last_reissued_at":"2026-07-05T06:28:33.166288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:33.166288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WACO: Word-Aligned Contrastive Learning for Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","submitted_at":"2022-12-19T10:49:35Z","abstract_excerpt":"End-to-end Speech Translation (E2E ST) aims to directly translate source speech into target text. Existing ST methods perform poorly when only extremely small speech-text data are available for training. We observe that an ST model's performance closely correlates with its embedding similarity between speech and source transcript. In this paper, we propose Word-Aligned COntrastive learning (WACO), a simple and effective method for extremely low-resource speech-to-text translation. Our key idea is bridging word-level representations for both speech and text modalities via contrastive learning. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09359","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/2212.09359/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":"2212.09359","created_at":"2026-07-05T06:28:33.166357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09359v3","created_at":"2026-07-05T06:28:33.166357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09359","created_at":"2026-07-05T06:28:33.166357+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOV344YSF2VG","created_at":"2026-07-05T06:28:33.166357+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOV344YSF2VGCACK","created_at":"2026-07-05T06:28:33.166357+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOV344YS","created_at":"2026-07-05T06:28:33.166357+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/LOV344YSF2VGCACK3KGE2Y5XEJ","json":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ.json","graph_json":"https://pith.science/api/pith-number/LOV344YSF2VGCACK3KGE2Y5XEJ/graph.json","events_json":"https://pith.science/api/pith-number/LOV344YSF2VGCACK3KGE2Y5XEJ/events.json","paper":"https://pith.science/paper/LOV344YS"},"agent_actions":{"view_html":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ","download_json":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ.json","view_paper":"https://pith.science/paper/LOV344YS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09359&json=true","fetch_graph":"https://pith.science/api/pith-number/LOV344YSF2VGCACK3KGE2Y5XEJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LOV344YSF2VGCACK3KGE2Y5XEJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ/action/storage_attestation","attest_author":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ/action/author_attestation","sign_citation":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ/action/citation_signature","submit_replication":"https://pith.science/pith/LOV344YSF2VGCACK3KGE2Y5XEJ/action/replication_record"}},"created_at":"2026-07-05T06:28:33.166357+00:00","updated_at":"2026-07-05T06:28:33.166357+00:00"}