{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UKV577Q3YR66E7JJGFTTP2QDJX","short_pith_number":"pith:UKV577Q3","schema_version":"1.0","canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","source":{"kind":"arxiv","id":"1806.06734","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Word Segmentation from Speech with Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Aline Villavicencio, Fran\\c{c}ois Yvon, Laurent Besacier, Lucas Ondel, Marcely Zanon-Boito, Pierre Godard","submitted_at":"2018-06-18T14:35:14Z","abstract_excerpt":"We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illus"},"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":"1806.06734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-18T14:35:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09c310e6cf1fefc7782ed6fee577ad976dbc65d50410b1181f6ea324cd020c57","abstract_canon_sha256":"0f977cf72fe9ae2833b54c0f5ec44177f5fbfffd6ddb0080c7db80af82f10086"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:59.284212Z","signature_b64":"pQZTIvNopdexA0aq4vkuGxOjYcJiZZmabmT7MyE9tNMnDP+C7E1FlFNk5eNr1Oq4H923OzAMsXgBLAtZZM8CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2abdffe1bc47de27d29316737ea034dc1e61fb57773a3641d03acac141b0f17","last_reissued_at":"2026-05-18T00:12:59.283554Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:59.283554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Word Segmentation from Speech with Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Berard, Aline Villavicencio, Fran\\c{c}ois Yvon, Laurent Besacier, Lucas Ondel, Marcely Zanon-Boito, Pierre Godard","submitted_at":"2018-06-18T14:35:14Z","abstract_excerpt":"We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL). Our methodology assumes a pairing between recordings in the UL with translations in a well-resourced language. It uses Acoustic Unit Discovery (AUD) to convert speech into a sequence of pseudo-phones that is segmented using neural soft-alignments produced by a neural machine translation model. Evaluation uses an actual Bantu UL, Mboshi; comparisons to monolingual and bilingual baselines illus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06734","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":""},"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":"1806.06734","created_at":"2026-05-18T00:12:59.283660+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06734v1","created_at":"2026-05-18T00:12:59.283660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06734","created_at":"2026-05-18T00:12:59.283660+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKV577Q3YR66","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKV577Q3YR66E7JJ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKV577Q3","created_at":"2026-05-18T12:32:56.356000+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/UKV577Q3YR66E7JJGFTTP2QDJX","json":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX.json","graph_json":"https://pith.science/api/pith-number/UKV577Q3YR66E7JJGFTTP2QDJX/graph.json","events_json":"https://pith.science/api/pith-number/UKV577Q3YR66E7JJGFTTP2QDJX/events.json","paper":"https://pith.science/paper/UKV577Q3"},"agent_actions":{"view_html":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX","download_json":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX.json","view_paper":"https://pith.science/paper/UKV577Q3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06734&json=true","fetch_graph":"https://pith.science/api/pith-number/UKV577Q3YR66E7JJGFTTP2QDJX/graph.json","fetch_events":"https://pith.science/api/pith-number/UKV577Q3YR66E7JJGFTTP2QDJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/action/storage_attestation","attest_author":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/action/author_attestation","sign_citation":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/action/citation_signature","submit_replication":"https://pith.science/pith/UKV577Q3YR66E7JJGFTTP2QDJX/action/replication_record"}},"created_at":"2026-05-18T00:12:59.283660+00:00","updated_at":"2026-05-18T00:12:59.283660+00:00"}