{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H7LVYKOVBUEYIFDQZSN5MCV7TY","short_pith_number":"pith:H7LVYKOV","schema_version":"1.0","canonical_sha256":"3fd75c29d50d09841470cc9bd60abf9e34522c9c228247c4cfc2582e72e7c806","source":{"kind":"arxiv","id":"2505.24713","version":1},"attestation_state":"computed","paper":{"title":"Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Badr M. Abdullah, Bernd M\\\"obius, Dietrich Klakow, Matthew Baas","submitted_at":"2025-05-30T15:36:08Z","abstract_excerpt":"Arabic dialect identification (ADI) systems are essential for large-scale data collection pipelines that enable the development of inclusive speech technologies for Arabic language varieties. However, the reliability of current ADI systems is limited by poor generalization to out-of-domain speech. In this paper, we present an effective approach based on voice conversion for training ADI models that achieves state-of-the-art performance and significantly improves robustness in cross-domain scenarios. Evaluated on a newly collected real-world test set spanning four different domains, our approac"},"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":"2505.24713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T15:36:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2cffa7813941720c3b2deabcd97cc881aaff791ec57b9d114c6b35af4ed48c42","abstract_canon_sha256":"449549c3730e27e8bd6d1301cc584092f46a2166cee1396f97a82b3de10a7b45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:55.243651Z","signature_b64":"vXPP/7Ct5ErLmky+5N4wzzoz6FYZ2T7VeokefoYQFJ89StDVt+E6rKe8uwjPy8tSHFbVzf73Omau3CKU8+X5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd75c29d50d09841470cc9bd60abf9e34522c9c228247c4cfc2582e72e7c806","last_reissued_at":"2026-07-05T11:12:55.243137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:55.243137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Badr M. Abdullah, Bernd M\\\"obius, Dietrich Klakow, Matthew Baas","submitted_at":"2025-05-30T15:36:08Z","abstract_excerpt":"Arabic dialect identification (ADI) systems are essential for large-scale data collection pipelines that enable the development of inclusive speech technologies for Arabic language varieties. However, the reliability of current ADI systems is limited by poor generalization to out-of-domain speech. In this paper, we present an effective approach based on voice conversion for training ADI models that achieves state-of-the-art performance and significantly improves robustness in cross-domain scenarios. Evaluated on a newly collected real-world test set spanning four different domains, our approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24713","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.24713/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2505.24713","created_at":"2026-07-05T11:12:55.243202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24713v1","created_at":"2026-07-05T11:12:55.243202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24713","created_at":"2026-07-05T11:12:55.243202+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7LVYKOVBUEY","created_at":"2026-07-05T11:12:55.243202+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7LVYKOVBUEYIFDQ","created_at":"2026-07-05T11:12:55.243202+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7LVYKOV","created_at":"2026-07-05T11:12:55.243202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24713","citing_title":"Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY","json":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY.json","graph_json":"https://pith.science/api/pith-number/H7LVYKOVBUEYIFDQZSN5MCV7TY/graph.json","events_json":"https://pith.science/api/pith-number/H7LVYKOVBUEYIFDQZSN5MCV7TY/events.json","paper":"https://pith.science/paper/H7LVYKOV"},"agent_actions":{"view_html":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY","download_json":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY.json","view_paper":"https://pith.science/paper/H7LVYKOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24713&json=true","fetch_graph":"https://pith.science/api/pith-number/H7LVYKOVBUEYIFDQZSN5MCV7TY/graph.json","fetch_events":"https://pith.science/api/pith-number/H7LVYKOVBUEYIFDQZSN5MCV7TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY/action/storage_attestation","attest_author":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY/action/author_attestation","sign_citation":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY/action/citation_signature","submit_replication":"https://pith.science/pith/H7LVYKOVBUEYIFDQZSN5MCV7TY/action/replication_record"}},"created_at":"2026-07-05T11:12:55.243202+00:00","updated_at":"2026-07-05T11:12:55.243202+00:00"}