{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RSAAD6FQPE6W2QOOOENUWJ4U7K","short_pith_number":"pith:RSAAD6FQ","schema_version":"1.0","canonical_sha256":"8c8001f8b0793d6d41ce711b4b2794faa7674328ef80e6dd866aa5333380e174","source":{"kind":"arxiv","id":"2407.21646","version":2},"attestation_state":"computed","paper":{"title":"Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hang Li, Lu Xu, Ningxin Peng, Qini Zhang, Shanbo Cheng, Tom Ko, Zhichao Huang","submitted_at":"2024-07-31T14:48:27Z","abstract_excerpt":"In this paper, we present Cross Language Agent -- Simultaneous Interpretation, CLASI, a high-quality and human-like Simultaneous Speech Translation (SiST) System. Inspired by professional human interpreters, we utilize a novel data-driven read-write strategy to balance the translation quality and latency. To address the challenge of translating in-domain terminologies, CLASI employs a multi-modal retrieving module to obtain relevant information to augment the translation. Supported by LLMs, our approach can generate error-tolerated translation by considering the input audio, historical context"},"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":"2407.21646","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-31T14:48:27Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"291c557486a0e1fca801c2e11742d1fe005d935c0a16fe5f36254356ef589908","abstract_canon_sha256":"ccf03ddf10b7a5785843a062a1b864f200d7491315843d45546e823029077286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:04.230713Z","signature_b64":"vKF5ECYtcxQKfDarCrco41u353vfMPzu7uxz6V5tjeGMkXN1YJkMgAM3OoSHBMW04UcXYdEJJvzs9lzSYv4OCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8001f8b0793d6d41ce711b4b2794faa7674328ef80e6dd866aa5333380e174","last_reissued_at":"2026-07-05T09:01:04.230193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:04.230193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Achieving Human Parity on End-to-end Simultaneous Speech Translation via LLM Agent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hang Li, Lu Xu, Ningxin Peng, Qini Zhang, Shanbo Cheng, Tom Ko, Zhichao Huang","submitted_at":"2024-07-31T14:48:27Z","abstract_excerpt":"In this paper, we present Cross Language Agent -- Simultaneous Interpretation, CLASI, a high-quality and human-like Simultaneous Speech Translation (SiST) System. Inspired by professional human interpreters, we utilize a novel data-driven read-write strategy to balance the translation quality and latency. To address the challenge of translating in-domain terminologies, CLASI employs a multi-modal retrieving module to obtain relevant information to augment the translation. Supported by LLMs, our approach can generate error-tolerated translation by considering the input audio, historical context"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21646","kind":"arxiv","version":2},"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/2407.21646/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":"2407.21646","created_at":"2026-07-05T09:01:04.230255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21646v2","created_at":"2026-07-05T09:01:04.230255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21646","created_at":"2026-07-05T09:01:04.230255+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSAAD6FQPE6W","created_at":"2026-07-05T09:01:04.230255+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSAAD6FQPE6W2QOO","created_at":"2026-07-05T09:01:04.230255+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSAAD6FQ","created_at":"2026-07-05T09:01:04.230255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16009","citing_title":"Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21045","citing_title":"Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09916","citing_title":"Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K","json":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K.json","graph_json":"https://pith.science/api/pith-number/RSAAD6FQPE6W2QOOOENUWJ4U7K/graph.json","events_json":"https://pith.science/api/pith-number/RSAAD6FQPE6W2QOOOENUWJ4U7K/events.json","paper":"https://pith.science/paper/RSAAD6FQ"},"agent_actions":{"view_html":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K","download_json":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K.json","view_paper":"https://pith.science/paper/RSAAD6FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21646&json=true","fetch_graph":"https://pith.science/api/pith-number/RSAAD6FQPE6W2QOOOENUWJ4U7K/graph.json","fetch_events":"https://pith.science/api/pith-number/RSAAD6FQPE6W2QOOOENUWJ4U7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K/action/storage_attestation","attest_author":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K/action/author_attestation","sign_citation":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K/action/citation_signature","submit_replication":"https://pith.science/pith/RSAAD6FQPE6W2QOOOENUWJ4U7K/action/replication_record"}},"created_at":"2026-07-05T09:01:04.230255+00:00","updated_at":"2026-07-05T09:01:04.230255+00:00"}