{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R6N23LCA7L2TXLOGQZHIXU6DQ7","short_pith_number":"pith:R6N23LCA","schema_version":"1.0","canonical_sha256":"8f9badac40faf53badc6864e8bd3c387ed59870dad978f4a57599d1571162e56","source":{"kind":"arxiv","id":"2010.14920","version":1},"attestation_state":"computed","paper":{"title":"Bridging the Modality Gap for Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Jiajun Zhang, Junnan Zhu, Yuchen Liu","submitted_at":"2020-10-28T12:33:04Z","abstract_excerpt":"End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and semantic information simultaneously, which ignores the speech-and-text modality differences and makes the encoder overloaded, leading to great difficulty in learning such a model. To address these issues, we propose a Speech-to-Text Adaptation for Speech Translation (STAST) model which aims to improve the end-to-end model performance by bridging the modalit"},"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":"2010.14920","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-28T12:33:04Z","cross_cats_sorted":[],"title_canon_sha256":"9d4af04df10a5cc2abc4cd4b59b962dd0276d425c0dea3b7ed05456437ec590c","abstract_canon_sha256":"a40c19d05d7c4e390c076b21ed33dd06cb192d749d901a9454f866b55e745da6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:19.257894Z","signature_b64":"p5Simkv2YGPA4IsR42PGOSIAtjZXA0ZX3KNVUjk0RuMwyk6+AI23JiOXa0kPCH4KnAZX6Lyk/RSkOgeNViLFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f9badac40faf53badc6864e8bd3c387ed59870dad978f4a57599d1571162e56","last_reissued_at":"2026-07-05T01:47:19.257428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:19.257428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Modality Gap for Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Jiajun Zhang, Junnan Zhu, Yuchen Liu","submitted_at":"2020-10-28T12:33:04Z","abstract_excerpt":"End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way. Most existing methods employ an encoder-decoder structure with a single encoder to learn acoustic representation and semantic information simultaneously, which ignores the speech-and-text modality differences and makes the encoder overloaded, leading to great difficulty in learning such a model. To address these issues, we propose a Speech-to-Text Adaptation for Speech Translation (STAST) model which aims to improve the end-to-end model performance by bridging the modalit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14920","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/2010.14920/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":"2010.14920","created_at":"2026-07-05T01:47:19.257483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.14920v1","created_at":"2026-07-05T01:47:19.257483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14920","created_at":"2026-07-05T01:47:19.257483+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6N23LCA7L2T","created_at":"2026-07-05T01:47:19.257483+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6N23LCA7L2TXLOG","created_at":"2026-07-05T01:47:19.257483+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6N23LCA","created_at":"2026-07-05T01:47:19.257483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05591","citing_title":"AI-Driven Modular Services for Accessible Multilingual Education in Immersive Extended Reality Settings: Integrating Speech Processing, Translation, and Sign Language Rendering","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7","json":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7.json","graph_json":"https://pith.science/api/pith-number/R6N23LCA7L2TXLOGQZHIXU6DQ7/graph.json","events_json":"https://pith.science/api/pith-number/R6N23LCA7L2TXLOGQZHIXU6DQ7/events.json","paper":"https://pith.science/paper/R6N23LCA"},"agent_actions":{"view_html":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7","download_json":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7.json","view_paper":"https://pith.science/paper/R6N23LCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.14920&json=true","fetch_graph":"https://pith.science/api/pith-number/R6N23LCA7L2TXLOGQZHIXU6DQ7/graph.json","fetch_events":"https://pith.science/api/pith-number/R6N23LCA7L2TXLOGQZHIXU6DQ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7/action/storage_attestation","attest_author":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7/action/author_attestation","sign_citation":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7/action/citation_signature","submit_replication":"https://pith.science/pith/R6N23LCA7L2TXLOGQZHIXU6DQ7/action/replication_record"}},"created_at":"2026-07-05T01:47:19.257483+00:00","updated_at":"2026-07-05T01:47:19.257483+00:00"}