{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BHTHPTNRRFPFAUSO3BUKH2OVHI","short_pith_number":"pith:BHTHPTNR","schema_version":"1.0","canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","source":{"kind":"arxiv","id":"1509.06928","version":2},"attestation_state":"computed","paper":{"title":"Automatic Dialect Detection in Arabic Broadcast Speech","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Ali, James Glass, Najim Dehak, Patrick Cardinal, Peter Bell, Sameer Khurana, Sree Harsha Yella, Steve Renals","submitted_at":"2015-09-23T11:41:10Z","abstract_excerpt":"We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of "},"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":"1509.06928","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-23T11:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"98ab0f92e576716f1955e6c8e00d9e94fadbf8639f0b958840558b13cc615795","abstract_canon_sha256":"3d2faf99402484114121c01ec50845f99859f33417a41ed276b6c71b74077100"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:29.699295Z","signature_b64":"rr6i+Q/px9wFzPxlPrWam4mfGOXnk22FF9cV6HEG35fhCrw5lEl+aAyH7zTYy2IRTGr+a3Yi24HGl0KdfCbEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09e677cdb1895e50524ed868a3e9d53a1555a66be989a0c727cd6431a2faf88e","last_reissued_at":"2026-05-18T01:09:29.698923Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:29.698923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Dialect Detection in Arabic Broadcast Speech","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmed Ali, James Glass, Najim Dehak, Patrick Cardinal, Peter Bell, Sameer Khurana, Sree Harsha Yella, Steve Renals","submitted_at":"2015-09-23T11:41:10Z","abstract_excerpt":"We investigate different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework. We studied both generative and discriminate classifiers, and we combined these features using a multi-class Support Vector Machine (SVM). We validated our results on an Arabic/English language identification task, with an accuracy of 100%. We used these features in a binary classifier to discriminate between Modern Standard Arabic (MSA) and Dialectal Arabic, with an accuracy of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06928","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":"1509.06928","created_at":"2026-05-18T01:09:29.698986+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.06928v2","created_at":"2026-05-18T01:09:29.698986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06928","created_at":"2026-05-18T01:09:29.698986+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHTHPTNRRFPF","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHTHPTNRRFPFAUSO","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHTHPTNR","created_at":"2026-05-18T12:29:14.074870+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/BHTHPTNRRFPFAUSO3BUKH2OVHI","json":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI.json","graph_json":"https://pith.science/api/pith-number/BHTHPTNRRFPFAUSO3BUKH2OVHI/graph.json","events_json":"https://pith.science/api/pith-number/BHTHPTNRRFPFAUSO3BUKH2OVHI/events.json","paper":"https://pith.science/paper/BHTHPTNR"},"agent_actions":{"view_html":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI","download_json":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI.json","view_paper":"https://pith.science/paper/BHTHPTNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.06928&json=true","fetch_graph":"https://pith.science/api/pith-number/BHTHPTNRRFPFAUSO3BUKH2OVHI/graph.json","fetch_events":"https://pith.science/api/pith-number/BHTHPTNRRFPFAUSO3BUKH2OVHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/action/storage_attestation","attest_author":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/action/author_attestation","sign_citation":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/action/citation_signature","submit_replication":"https://pith.science/pith/BHTHPTNRRFPFAUSO3BUKH2OVHI/action/replication_record"}},"created_at":"2026-05-18T01:09:29.698986+00:00","updated_at":"2026-05-18T01:09:29.698986+00:00"}