{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3ARCM7IXLSBEP4QJNIOIIA4AGR","short_pith_number":"pith:3ARCM7IX","schema_version":"1.0","canonical_sha256":"d822267d175c8247f2096a1c8403803456077dba8d6e80760b9f5fdf3c286b04","source":{"kind":"arxiv","id":"1807.06204","version":2},"attestation_state":"computed","paper":{"title":"Low-Resource Contextual Topic Identification on Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunxi Liu, Craig Harman, Jan Trmal, Matthew Wiesner, Najim Dehak, Sanjeev Khudanpur, Shinji Watanabe","submitted_at":"2018-07-17T04:01:06Z","abstract_excerpt":"In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose method for topic ID on spoken segments in low-resource languages, using a cascade of universal acoustic modeling, translation lexicons to English, and English-language topic classification. Next, instead of classifying each segment independently, we demonstrate that exploring the contextual dependencies across sequential segments can provide large improvements. I"},"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":"1807.06204","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-17T04:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"c04a013929202c2e1091f67d0ec9aa7298b750ce399f736111d4cb370d03b203","abstract_canon_sha256":"696f7447268a5ba6993e7c1bae56d23c52e3c2fde5f28bdee49da271a6961597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:29.556332Z","signature_b64":"sqejeJaXUyPJgh+L8yhy6VpFu2Ar4Y8cFSzAR3ft6kvI5e2HvO2xaj+f4r+irhxbUGYMvKf0OLs1i4TlSuWvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d822267d175c8247f2096a1c8403803456077dba8d6e80760b9f5fdf3c286b04","last_reissued_at":"2026-05-18T00:04:29.555920Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:29.555920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Contextual Topic Identification on Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunxi Liu, Craig Harman, Jan Trmal, Matthew Wiesner, Najim Dehak, Sanjeev Khudanpur, Shinji Watanabe","submitted_at":"2018-07-17T04:01:06Z","abstract_excerpt":"In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose method for topic ID on spoken segments in low-resource languages, using a cascade of universal acoustic modeling, translation lexicons to English, and English-language topic classification. Next, instead of classifying each segment independently, we demonstrate that exploring the contextual dependencies across sequential segments can provide large improvements. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06204","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":"1807.06204","created_at":"2026-05-18T00:04:29.555982+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06204v2","created_at":"2026-05-18T00:04:29.555982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06204","created_at":"2026-05-18T00:04:29.555982+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ARCM7IXLSBE","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ARCM7IXLSBEP4QJ","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ARCM7IX","created_at":"2026-05-18T12:32:02.567920+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/3ARCM7IXLSBEP4QJNIOIIA4AGR","json":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR.json","graph_json":"https://pith.science/api/pith-number/3ARCM7IXLSBEP4QJNIOIIA4AGR/graph.json","events_json":"https://pith.science/api/pith-number/3ARCM7IXLSBEP4QJNIOIIA4AGR/events.json","paper":"https://pith.science/paper/3ARCM7IX"},"agent_actions":{"view_html":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR","download_json":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR.json","view_paper":"https://pith.science/paper/3ARCM7IX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06204&json=true","fetch_graph":"https://pith.science/api/pith-number/3ARCM7IXLSBEP4QJNIOIIA4AGR/graph.json","fetch_events":"https://pith.science/api/pith-number/3ARCM7IXLSBEP4QJNIOIIA4AGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR/action/storage_attestation","attest_author":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR/action/author_attestation","sign_citation":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR/action/citation_signature","submit_replication":"https://pith.science/pith/3ARCM7IXLSBEP4QJNIOIIA4AGR/action/replication_record"}},"created_at":"2026-05-18T00:04:29.555982+00:00","updated_at":"2026-05-18T00:04:29.555982+00:00"}