{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7PV7Q7CML63H4IH7QW7LIKO73Y","short_pith_number":"pith:7PV7Q7CM","schema_version":"1.0","canonical_sha256":"fbebf87c4c5fb67e20ff85beb429dfde01ff3951bf5f494c11cabff0c0004406","source":{"kind":"arxiv","id":"2310.11141","version":1},"attestation_state":"computed","paper":{"title":"Long-form Simultaneous Speech Translation: Thesis Proposal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Peter Pol\\'ak","submitted_at":"2023-10-17T10:44:05Z","abstract_excerpt":"Simultaneous speech translation (SST) aims to provide real-time translation of spoken language, even before the speaker finishes their sentence. Traditionally, SST has been addressed primarily by cascaded systems that decompose the task into subtasks, including speech recognition, segmentation, and machine translation. However, the advent of deep learning has sparked significant interest in end-to-end (E2E) systems. Nevertheless, a major limitation of most approaches to E2E SST reported in the current literature is that they assume that the source speech is pre-segmented into sentences, which "},"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":"2310.11141","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-17T10:44:05Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"605d59cb32cc178cc9ae790410c71e5a9ff419e59f687ffec1339dc318e4a450","abstract_canon_sha256":"04443fbfead2b647b010fea2975d86354d76930d4c600e2d94dc4d0e2ea6beab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:51.067204Z","signature_b64":"rpFG2ZTG8Wryr/52AbutnEzc7pPR9q58CnuN3IbhyVxBD69/HUIMEW3Xj2hxI0UF9Mb4qMne+AWnWGJ+i7XVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbebf87c4c5fb67e20ff85beb429dfde01ff3951bf5f494c11cabff0c0004406","last_reissued_at":"2026-07-05T07:01:51.066836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:51.066836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-form Simultaneous Speech Translation: Thesis Proposal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Peter Pol\\'ak","submitted_at":"2023-10-17T10:44:05Z","abstract_excerpt":"Simultaneous speech translation (SST) aims to provide real-time translation of spoken language, even before the speaker finishes their sentence. Traditionally, SST has been addressed primarily by cascaded systems that decompose the task into subtasks, including speech recognition, segmentation, and machine translation. However, the advent of deep learning has sparked significant interest in end-to-end (E2E) systems. Nevertheless, a major limitation of most approaches to E2E SST reported in the current literature is that they assume that the source speech is pre-segmented into sentences, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11141","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/2310.11141/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":"2310.11141","created_at":"2026-07-05T07:01:51.066894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11141v1","created_at":"2026-07-05T07:01:51.066894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11141","created_at":"2026-07-05T07:01:51.066894+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PV7Q7CML63H","created_at":"2026-07-05T07:01:51.066894+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PV7Q7CML63H4IH7","created_at":"2026-07-05T07:01:51.066894+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PV7Q7CM","created_at":"2026-07-05T07:01:51.066894+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/7PV7Q7CML63H4IH7QW7LIKO73Y","json":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y.json","graph_json":"https://pith.science/api/pith-number/7PV7Q7CML63H4IH7QW7LIKO73Y/graph.json","events_json":"https://pith.science/api/pith-number/7PV7Q7CML63H4IH7QW7LIKO73Y/events.json","paper":"https://pith.science/paper/7PV7Q7CM"},"agent_actions":{"view_html":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y","download_json":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y.json","view_paper":"https://pith.science/paper/7PV7Q7CM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11141&json=true","fetch_graph":"https://pith.science/api/pith-number/7PV7Q7CML63H4IH7QW7LIKO73Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7PV7Q7CML63H4IH7QW7LIKO73Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y/action/storage_attestation","attest_author":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y/action/author_attestation","sign_citation":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y/action/citation_signature","submit_replication":"https://pith.science/pith/7PV7Q7CML63H4IH7QW7LIKO73Y/action/replication_record"}},"created_at":"2026-07-05T07:01:51.066894+00:00","updated_at":"2026-07-05T07:01:51.066894+00:00"}