{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:X4M5K4UKAMWHSNCGDXECEWK2KE","short_pith_number":"pith:X4M5K4UK","schema_version":"1.0","canonical_sha256":"bf19d5728a032c7934461dc822595a513e696309c4e8a5aa2bad1c422d2cf5cb","source":{"kind":"arxiv","id":"1802.06053","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Models for Unit Discovery on a Very Low Resource Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elin Larsen, Emmanuel Dupoux, Fran\\c{c}ois Yvon, Laurent Besacier, Lucas Ondel, Lukas Burget, Mark Hasegawa-Johnson, Odette Scharenborg, Pierre Godard, Sanjeev Khudanpur","submitted_at":"2018-02-16T17:58:43Z","abstract_excerpt":"Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are"},"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":"1802.06053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-02-16T17:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"c359d55ed58af1f095309d43ea235eda54efc4f70c281694e72758278f8d09ef","abstract_canon_sha256":"aa2b3476c25e28f71673e7da86066b8080796d61f66f44a7afd8f7dc25b99bd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:54.396895Z","signature_b64":"ET9X4rW5CZEkoK1IoSWUXMNVo0RWDV8rM4lrnPS+KR4GjFiLqzUQg8VqJoE9JsVPDf1c5nxfmWnAwedYQsGtAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf19d5728a032c7934461dc822595a513e696309c4e8a5aa2bad1c422d2cf5cb","last_reissued_at":"2026-05-18T00:22:54.396434Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:54.396434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Models for Unit Discovery on a Very Low Resource Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elin Larsen, Emmanuel Dupoux, Fran\\c{c}ois Yvon, Laurent Besacier, Lucas Ondel, Lukas Burget, Mark Hasegawa-Johnson, Odette Scharenborg, Pierre Godard, Sanjeev Khudanpur","submitted_at":"2018-02-16T17:58:43Z","abstract_excerpt":"Developing speech technologies for low-resource languages has become a very active research field over the last decade. Among others, Bayesian models have shown some promising results on artificial examples but still lack of in situ experiments. Our work applies state-of-the-art Bayesian models to unsupervised Acoustic Unit Discovery (AUD) in a real low-resource language scenario. We also show that Bayesian models can naturally integrate information from other resourceful languages by means of informative prior leading to more consistent discovered units. Finally, discovered acoustic units are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06053","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":""},"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":"1802.06053","created_at":"2026-05-18T00:22:54.396498+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06053v2","created_at":"2026-05-18T00:22:54.396498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06053","created_at":"2026-05-18T00:22:54.396498+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4M5K4UKAMWH","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4M5K4UKAMWHSNCG","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4M5K4UK","created_at":"2026-05-18T12:33:01.666342+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/X4M5K4UKAMWHSNCGDXECEWK2KE","json":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE.json","graph_json":"https://pith.science/api/pith-number/X4M5K4UKAMWHSNCGDXECEWK2KE/graph.json","events_json":"https://pith.science/api/pith-number/X4M5K4UKAMWHSNCGDXECEWK2KE/events.json","paper":"https://pith.science/paper/X4M5K4UK"},"agent_actions":{"view_html":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE","download_json":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE.json","view_paper":"https://pith.science/paper/X4M5K4UK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06053&json=true","fetch_graph":"https://pith.science/api/pith-number/X4M5K4UKAMWHSNCGDXECEWK2KE/graph.json","fetch_events":"https://pith.science/api/pith-number/X4M5K4UKAMWHSNCGDXECEWK2KE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE/action/storage_attestation","attest_author":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE/action/author_attestation","sign_citation":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE/action/citation_signature","submit_replication":"https://pith.science/pith/X4M5K4UKAMWHSNCGDXECEWK2KE/action/replication_record"}},"created_at":"2026-05-18T00:22:54.396498+00:00","updated_at":"2026-05-18T00:22:54.396498+00:00"}