{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4DQKDA23V36DQRPGP2JJUPMZ4","short_pith_number":"pith:T4DQKDA2","schema_version":"1.0","canonical_sha256":"9f07050c1add77e1c22f33f494d1eccf1c7e407833ea7e3df9772c03b6baa5fe","source":{"kind":"arxiv","id":"2410.23323","version":3},"attestation_state":"computed","paper":{"title":"Phonology-Guided Speech-to-Speech Translation for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","authors_text":"Dennis Kaburu, Peter Ochieng","submitted_at":"2024-10-30T09:44:52Z","abstract_excerpt":"We present a prosody-guided framework for speech-to-speech translation (S2ST) that aligns and translates speech \\emph{without} transcripts by leveraging cross-linguistic pause synchrony. Analyzing a 6{,}000-hour East African news corpus spanning five languages, we show that \\emph{within-phylum} language pairs exhibit 30--40\\% lower pause variance and over 3$\\times$ higher onset/offset correlation compared to cross-phylum pairs. These findings motivate \\textbf{SPaDA}, a dynamic-programming alignment algorithm that integrates silence consistency, rate synchrony, and semantic similarity. SPaDA im"},"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":"2410.23323","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-30T09:44:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"63e01576e180e979ab1aa5aa3f97f8d7cda04a8e94922eb6ff770c3325475d5e","abstract_canon_sha256":"1c0063ce4232fafc44997f290966d1fd4f02abed0c5e593ecc79e1447d5ca3e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:22.300133Z","signature_b64":"ql/iu6cxDmjLDC9fEZR7iMzthq/Byau9LgG9rWTwByzFyUKXRZPek2xcNpBvBy38zjZ9sV8ZEZnwdR04jeZ/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f07050c1add77e1c22f33f494d1eccf1c7e407833ea7e3df9772c03b6baa5fe","last_reissued_at":"2026-07-05T11:19:22.299637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:22.299637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phonology-Guided Speech-to-Speech Translation for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"eess.AS","authors_text":"Dennis Kaburu, Peter Ochieng","submitted_at":"2024-10-30T09:44:52Z","abstract_excerpt":"We present a prosody-guided framework for speech-to-speech translation (S2ST) that aligns and translates speech \\emph{without} transcripts by leveraging cross-linguistic pause synchrony. Analyzing a 6{,}000-hour East African news corpus spanning five languages, we show that \\emph{within-phylum} language pairs exhibit 30--40\\% lower pause variance and over 3$\\times$ higher onset/offset correlation compared to cross-phylum pairs. These findings motivate \\textbf{SPaDA}, a dynamic-programming alignment algorithm that integrates silence consistency, rate synchrony, and semantic similarity. SPaDA im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23323","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/2410.23323/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":"2410.23323","created_at":"2026-07-05T11:19:22.299698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23323v3","created_at":"2026-07-05T11:19:22.299698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23323","created_at":"2026-07-05T11:19:22.299698+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4DQKDA23V36","created_at":"2026-07-05T11:19:22.299698+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4DQKDA23V36DQRP","created_at":"2026-07-05T11:19:22.299698+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4DQKDA2","created_at":"2026-07-05T11:19:22.299698+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":98,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4","json":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4.json","graph_json":"https://pith.science/api/pith-number/T4DQKDA23V36DQRPGP2JJUPMZ4/graph.json","events_json":"https://pith.science/api/pith-number/T4DQKDA23V36DQRPGP2JJUPMZ4/events.json","paper":"https://pith.science/paper/T4DQKDA2"},"agent_actions":{"view_html":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4","download_json":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4.json","view_paper":"https://pith.science/paper/T4DQKDA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23323&json=true","fetch_graph":"https://pith.science/api/pith-number/T4DQKDA23V36DQRPGP2JJUPMZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/T4DQKDA23V36DQRPGP2JJUPMZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4/action/storage_attestation","attest_author":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4/action/author_attestation","sign_citation":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4/action/citation_signature","submit_replication":"https://pith.science/pith/T4DQKDA23V36DQRPGP2JJUPMZ4/action/replication_record"}},"created_at":"2026-07-05T11:19:22.299698+00:00","updated_at":"2026-07-05T11:19:22.299698+00:00"}