{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GEXHU55NYLECYRQXP5KCI7IQNO","short_pith_number":"pith:GEXHU55N","schema_version":"1.0","canonical_sha256":"312e7a77adc2c82c46177f54247d106b898efaf37dc8a69c29c5b959d7252e0a","source":{"kind":"arxiv","id":"1706.00321","version":1},"attestation_state":"computed","paper":{"title":"Using of heterogeneous corpora for training of an ASR system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaurav Kumar, Jan Trmal, Matt Post, Paul McNamee, Sanjeev Khudanpur, Vimal Manohar","submitted_at":"2017-06-01T14:30:19Z","abstract_excerpt":"The paper summarizes the development of the LVCSR system built as a part of the Pashto speech-translation system at the SCALE (Summer Camp for Applied Language Exploration) 2015 workshop on \"Speech-to-text-translation for low-resource languages\". The Pashto language was chosen as a good \"proxy\" low-resource language, exhibiting multiple phenomena which make the speech-recognition and and speech-to-text-translation systems development hard.\n  Even when the amount of data is seemingly sufficient, given the fact that the data originates from multiple sources, the preliminary experiments reveal th"},"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":"1706.00321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-01T14:30:19Z","cross_cats_sorted":[],"title_canon_sha256":"f4432c75b94ce4bf26a1c6623ee2d768351eb41dc86ae4310dcfebb9d3fc16c5","abstract_canon_sha256":"d900336af7a40e7d89ecdc46b7bda7bab431ebc5360398205156e63a535f944e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:14.358014Z","signature_b64":"8p8hBFtvHBdyRysljFZnBQILXbPgJbeRN9S6WQ0fwXA7HP5L78j5Gn9ddiEYDAH5i1Y4zxgRzEXP/OUgEkyLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"312e7a77adc2c82c46177f54247d106b898efaf37dc8a69c29c5b959d7252e0a","last_reissued_at":"2026-05-18T00:43:14.357489Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:14.357489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using of heterogeneous corpora for training of an ASR system","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gaurav Kumar, Jan Trmal, Matt Post, Paul McNamee, Sanjeev Khudanpur, Vimal Manohar","submitted_at":"2017-06-01T14:30:19Z","abstract_excerpt":"The paper summarizes the development of the LVCSR system built as a part of the Pashto speech-translation system at the SCALE (Summer Camp for Applied Language Exploration) 2015 workshop on \"Speech-to-text-translation for low-resource languages\". The Pashto language was chosen as a good \"proxy\" low-resource language, exhibiting multiple phenomena which make the speech-recognition and and speech-to-text-translation systems development hard.\n  Even when the amount of data is seemingly sufficient, given the fact that the data originates from multiple sources, the preliminary experiments reveal th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00321","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":"1706.00321","created_at":"2026-05-18T00:43:14.357579+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.00321v1","created_at":"2026-05-18T00:43:14.357579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00321","created_at":"2026-05-18T00:43:14.357579+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEXHU55NYLEC","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEXHU55NYLECYRQX","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEXHU55N","created_at":"2026-05-18T12:31:15.632608+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/GEXHU55NYLECYRQXP5KCI7IQNO","json":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO.json","graph_json":"https://pith.science/api/pith-number/GEXHU55NYLECYRQXP5KCI7IQNO/graph.json","events_json":"https://pith.science/api/pith-number/GEXHU55NYLECYRQXP5KCI7IQNO/events.json","paper":"https://pith.science/paper/GEXHU55N"},"agent_actions":{"view_html":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO","download_json":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO.json","view_paper":"https://pith.science/paper/GEXHU55N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.00321&json=true","fetch_graph":"https://pith.science/api/pith-number/GEXHU55NYLECYRQXP5KCI7IQNO/graph.json","fetch_events":"https://pith.science/api/pith-number/GEXHU55NYLECYRQXP5KCI7IQNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO/action/storage_attestation","attest_author":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO/action/author_attestation","sign_citation":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO/action/citation_signature","submit_replication":"https://pith.science/pith/GEXHU55NYLECYRQXP5KCI7IQNO/action/replication_record"}},"created_at":"2026-05-18T00:43:14.357579+00:00","updated_at":"2026-05-18T00:43:14.357579+00:00"}