{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DCVPF4PPNKQZK37324UDZK2TGZ","short_pith_number":"pith:DCVPF4PP","schema_version":"1.0","canonical_sha256":"18aaf2f1ef6aa1956ffbd7283cab5336557cf0b134bf8fa080b0902edbb87feb","source":{"kind":"arxiv","id":"2411.14453","version":1},"attestation_state":"computed","paper":{"title":"Direct Speech-to-Speech Neural Machine Translation: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chandresh Kumar Maurya, Mahendra Gupta, Maitreyee Dutta","submitted_at":"2024-11-13T13:01:21Z","abstract_excerpt":"Speech-to-Speech Translation (S2ST) models transform speech from one language to another target language with the same linguistic information. S2ST is important for bridging the communication gap among communities and has diverse applications. In recent years, researchers have introduced direct S2ST models, which have the potential to translate speech without relying on intermediate text generation, have better decoding latency, and the ability to preserve paralinguistic and non-linguistic features. However, direct S2ST has yet to achieve quality performance for seamless communication and stil"},"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":"2411.14453","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T13:01:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"559663e03886fe944e7cfdaf8fdacd3eb689440707408a35921b2d33d49e0df6","abstract_canon_sha256":"c13f774cb64e9d17d306f7b85d99aa86c6417a0b907d65a6906251b6d2324bdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:51.342429Z","signature_b64":"kMJpvdTBHogYjThTpbwrM5mzDEQIn6eHp4sh1pUWrSXYoRT4ggzTDi4KiPuOzHq42RDucJ7vlsWcs6diJGG1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18aaf2f1ef6aa1956ffbd7283cab5336557cf0b134bf8fa080b0902edbb87feb","last_reissued_at":"2026-07-05T09:38:51.342019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:51.342019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct Speech-to-Speech Neural Machine Translation: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chandresh Kumar Maurya, Mahendra Gupta, Maitreyee Dutta","submitted_at":"2024-11-13T13:01:21Z","abstract_excerpt":"Speech-to-Speech Translation (S2ST) models transform speech from one language to another target language with the same linguistic information. S2ST is important for bridging the communication gap among communities and has diverse applications. In recent years, researchers have introduced direct S2ST models, which have the potential to translate speech without relying on intermediate text generation, have better decoding latency, and the ability to preserve paralinguistic and non-linguistic features. However, direct S2ST has yet to achieve quality performance for seamless communication and stil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14453","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/2411.14453/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":"2411.14453","created_at":"2026-07-05T09:38:51.342077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14453v1","created_at":"2026-07-05T09:38:51.342077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14453","created_at":"2026-07-05T09:38:51.342077+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCVPF4PPNKQZ","created_at":"2026-07-05T09:38:51.342077+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCVPF4PPNKQZK373","created_at":"2026-07-05T09:38:51.342077+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCVPF4PP","created_at":"2026-07-05T09:38:51.342077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02443","citing_title":"Breaking the Barriers of Text-Hungry and Audio-Deficient AI","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ","json":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ.json","graph_json":"https://pith.science/api/pith-number/DCVPF4PPNKQZK37324UDZK2TGZ/graph.json","events_json":"https://pith.science/api/pith-number/DCVPF4PPNKQZK37324UDZK2TGZ/events.json","paper":"https://pith.science/paper/DCVPF4PP"},"agent_actions":{"view_html":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ","download_json":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ.json","view_paper":"https://pith.science/paper/DCVPF4PP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14453&json=true","fetch_graph":"https://pith.science/api/pith-number/DCVPF4PPNKQZK37324UDZK2TGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DCVPF4PPNKQZK37324UDZK2TGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ/action/storage_attestation","attest_author":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ/action/author_attestation","sign_citation":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ/action/citation_signature","submit_replication":"https://pith.science/pith/DCVPF4PPNKQZK37324UDZK2TGZ/action/replication_record"}},"created_at":"2026-07-05T09:38:51.342077+00:00","updated_at":"2026-07-05T09:38:51.342077+00:00"}