{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UDAYDFYRT4FKEVSGT774S2L5IE","short_pith_number":"pith:UDAYDFYR","schema_version":"1.0","canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","source":{"kind":"arxiv","id":"1907.01302","version":1},"attestation_state":"computed","paper":{"title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mortaza (Morrie) Doulaty, Thomas Hain","submitted_at":"2019-07-02T11:33:52Z","abstract_excerpt":"Selecting in-domain data from a large pool of diverse and out-of-domain data is a non-trivial problem. In most cases simply using all of the available data will lead to sub-optimal and in some cases even worse performance compared to carefully selecting a matching set. This is true even for data-inefficient neural models. Acoustic Latent Dirichlet Allocation (aLDA) is shown to be useful in a variety of speech technology related tasks, including domain adaptation of acoustic models for automatic speech recognition and entity labeling for information retrieval. In this paper we propose to use aL"},"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":"1907.01302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-02T11:33:52Z","cross_cats_sorted":[],"title_canon_sha256":"c4df225362d715588a3da2a128b3be9ccf59472638d1c7daa00473ff9f776a94","abstract_canon_sha256":"4292466b9e849e222ce1f42bebbcfe81fa2f6f64d72b557fc162e35c83c38225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:40.719466Z","signature_b64":"jgjNCRj+djdJ9llvT3j3lmMYsRZ7AgGlINOhCs3NvYmtiBACssbHWfKkrfW8euuXTzefATO3clWNDyzfvlYdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0c18197119f0aa256469fffc9697d4101ea17b5e66bac3e9e6fb283c315eab2","last_reissued_at":"2026-05-17T23:41:40.718949Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:40.718949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mortaza (Morrie) Doulaty, Thomas Hain","submitted_at":"2019-07-02T11:33:52Z","abstract_excerpt":"Selecting in-domain data from a large pool of diverse and out-of-domain data is a non-trivial problem. In most cases simply using all of the available data will lead to sub-optimal and in some cases even worse performance compared to carefully selecting a matching set. This is true even for data-inefficient neural models. Acoustic Latent Dirichlet Allocation (aLDA) is shown to be useful in a variety of speech technology related tasks, including domain adaptation of acoustic models for automatic speech recognition and entity labeling for information retrieval. In this paper we propose to use aL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.01302","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":"1907.01302","created_at":"2026-05-17T23:41:40.719014+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.01302v1","created_at":"2026-05-17T23:41:40.719014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.01302","created_at":"2026-05-17T23:41:40.719014+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDAYDFYRT4FK","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDAYDFYRT4FKEVSG","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDAYDFYR","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01302","citing_title":"Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE","json":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE.json","graph_json":"https://pith.science/api/pith-number/UDAYDFYRT4FKEVSGT774S2L5IE/graph.json","events_json":"https://pith.science/api/pith-number/UDAYDFYRT4FKEVSGT774S2L5IE/events.json","paper":"https://pith.science/paper/UDAYDFYR"},"agent_actions":{"view_html":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE","download_json":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE.json","view_paper":"https://pith.science/paper/UDAYDFYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.01302&json=true","fetch_graph":"https://pith.science/api/pith-number/UDAYDFYRT4FKEVSGT774S2L5IE/graph.json","fetch_events":"https://pith.science/api/pith-number/UDAYDFYRT4FKEVSGT774S2L5IE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/action/storage_attestation","attest_author":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/action/author_attestation","sign_citation":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/action/citation_signature","submit_replication":"https://pith.science/pith/UDAYDFYRT4FKEVSGT774S2L5IE/action/replication_record"}},"created_at":"2026-05-17T23:41:40.719014+00:00","updated_at":"2026-05-17T23:41:40.719014+00:00"}