{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EKPZU5WSEZ627YEJ2ZGGF447FI","short_pith_number":"pith:EKPZU5WS","schema_version":"1.0","canonical_sha256":"229f9a76d2267dafe089d64c62f39f2a22baca88dcc2d35b2a4355b44c622f30","source":{"kind":"arxiv","id":"2105.03095","version":3},"attestation_state":"computed","paper":{"title":"Learning Shared Semantic Space for Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Han, Heng Ji, Lei Li, Mingxuan Wang","submitted_at":"2021-05-07T07:49:56Z","abstract_excerpt":"Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data and its end-to-end models incompatible with their ST counterparts. In observation of this obstacle, we propose to bridge this representation gap with Chimera. By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and"},"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":"2105.03095","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T07:49:56Z","cross_cats_sorted":[],"title_canon_sha256":"77150c87db993136af19c3dff81a6c1ec7ff8137c5c64a84b762da68fbd6cfd4","abstract_canon_sha256":"4558c6f4d2a8a2dbcbf49e94da1f907f5f5eb156db41eb3bed72195673d2b411"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:28.450215Z","signature_b64":"2HRpzgdQtH7KldpbsNJ0sIPPub5fNy6+9ktLmtHspLu8tGOs5UVAaJZ/6n9I4xLxt9eP+NX4B2/h+t4pHMkNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"229f9a76d2267dafe089d64c62f39f2a22baca88dcc2d35b2a4355b44c622f30","last_reissued_at":"2026-07-05T03:03:28.449762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:28.449762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Shared Semantic Space for Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Han, Heng Ji, Lei Li, Mingxuan Wang","submitted_at":"2021-05-07T07:49:56Z","abstract_excerpt":"Having numerous potential applications and great impact, end-to-end speech translation (ST) has long been treated as an independent task, failing to fully draw strength from the rapid advances of its sibling - text machine translation (MT). With text and audio inputs represented differently, the modality gap has rendered MT data and its end-to-end models incompatible with their ST counterparts. In observation of this obstacle, we propose to bridge this representation gap with Chimera. By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03095","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/2105.03095/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":"2105.03095","created_at":"2026-07-05T03:03:28.449818+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.03095v3","created_at":"2026-07-05T03:03:28.449818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03095","created_at":"2026-07-05T03:03:28.449818+00:00"},{"alias_kind":"pith_short_12","alias_value":"EKPZU5WSEZ62","created_at":"2026-07-05T03:03:28.449818+00:00"},{"alias_kind":"pith_short_16","alias_value":"EKPZU5WSEZ627YEJ","created_at":"2026-07-05T03:03:28.449818+00:00"},{"alias_kind":"pith_short_8","alias_value":"EKPZU5WS","created_at":"2026-07-05T03:03:28.449818+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12145","citing_title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12145","citing_title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI","json":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI.json","graph_json":"https://pith.science/api/pith-number/EKPZU5WSEZ627YEJ2ZGGF447FI/graph.json","events_json":"https://pith.science/api/pith-number/EKPZU5WSEZ627YEJ2ZGGF447FI/events.json","paper":"https://pith.science/paper/EKPZU5WS"},"agent_actions":{"view_html":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI","download_json":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI.json","view_paper":"https://pith.science/paper/EKPZU5WS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.03095&json=true","fetch_graph":"https://pith.science/api/pith-number/EKPZU5WSEZ627YEJ2ZGGF447FI/graph.json","fetch_events":"https://pith.science/api/pith-number/EKPZU5WSEZ627YEJ2ZGGF447FI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI/action/storage_attestation","attest_author":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI/action/author_attestation","sign_citation":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI/action/citation_signature","submit_replication":"https://pith.science/pith/EKPZU5WSEZ627YEJ2ZGGF447FI/action/replication_record"}},"created_at":"2026-07-05T03:03:28.449818+00:00","updated_at":"2026-07-05T03:03:28.449818+00:00"}