{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BTMHT7BR4LVMF5YSWRHZIELUNW","short_pith_number":"pith:BTMHT7BR","schema_version":"1.0","canonical_sha256":"0cd879fc31e2eac2f712b44f9411746d804804da33e749db981e81a726d45319","source":{"kind":"arxiv","id":"1706.03747","version":1},"attestation_state":"computed","paper":{"title":"Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Povey, Sanjeev Khudanpur, Vimal Manohar, Xiaohui Zhang","submitted_at":"2017-06-12T17:35:41Z","abstract_excerpt":"Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not available, but for which transcribed data exists. Our method integrates information from the letter sequence and from the acoustic evidence. The novel aspect of the problem that we address is the problem of how to prune entries from such a lexicon (since, empirically, lexicons with too many entries do not tend to be good for ASR performance). Experiments on"},"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":"1706.03747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-12T17:35:41Z","cross_cats_sorted":[],"title_canon_sha256":"4df0cd1af6202f223ab0d8cd0c869d2d8ab616cf67c3619b30509c484980de7d","abstract_canon_sha256":"ae97c884fd015239995edf88176559ba86f3d95e1968681fc3aab0e25e3f426c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:33.852452Z","signature_b64":"AElMnqRJCgtOyL/hbDt0EjxWaOtvHhXG9Mc3wCYZN81ZZ7FKoNbKAbxJ2+e9dVpHVTELRAm1va7abOwTnYRoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cd879fc31e2eac2f712b44f9411746d804804da33e749db981e81a726d45319","last_reissued_at":"2026-05-18T00:42:33.851696Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:33.851696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Povey, Sanjeev Khudanpur, Vimal Manohar, Xiaohui Zhang","submitted_at":"2017-06-12T17:35:41Z","abstract_excerpt":"Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not available, but for which transcribed data exists. Our method integrates information from the letter sequence and from the acoustic evidence. The novel aspect of the problem that we address is the problem of how to prune entries from such a lexicon (since, empirically, lexicons with too many entries do not tend to be good for ASR performance). Experiments on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.03747","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":"1706.03747","created_at":"2026-05-18T00:42:33.851864+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.03747v1","created_at":"2026-05-18T00:42:33.851864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.03747","created_at":"2026-05-18T00:42:33.851864+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTMHT7BR4LVM","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTMHT7BR4LVMF5YS","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTMHT7BR","created_at":"2026-05-18T12:31:08.081275+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/BTMHT7BR4LVMF5YSWRHZIELUNW","json":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW.json","graph_json":"https://pith.science/api/pith-number/BTMHT7BR4LVMF5YSWRHZIELUNW/graph.json","events_json":"https://pith.science/api/pith-number/BTMHT7BR4LVMF5YSWRHZIELUNW/events.json","paper":"https://pith.science/paper/BTMHT7BR"},"agent_actions":{"view_html":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW","download_json":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW.json","view_paper":"https://pith.science/paper/BTMHT7BR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.03747&json=true","fetch_graph":"https://pith.science/api/pith-number/BTMHT7BR4LVMF5YSWRHZIELUNW/graph.json","fetch_events":"https://pith.science/api/pith-number/BTMHT7BR4LVMF5YSWRHZIELUNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW/action/storage_attestation","attest_author":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW/action/author_attestation","sign_citation":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW/action/citation_signature","submit_replication":"https://pith.science/pith/BTMHT7BR4LVMF5YSWRHZIELUNW/action/replication_record"}},"created_at":"2026-05-18T00:42:33.851864+00:00","updated_at":"2026-05-18T00:42:33.851864+00:00"}