{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C6IE7ZG3A3EPHFPFQ35ZRMZS7C","short_pith_number":"pith:C6IE7ZG3","schema_version":"1.0","canonical_sha256":"17904fe4db06c8f395e586fb98b332f890341a779d1fa3125b0aa3db4416af4e","source":{"kind":"arxiv","id":"2312.07338","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Badr M. Abdullah, Dietrich Klakow, Mohammed Maqsood Shaik","submitted_at":"2023-12-12T14:58:08Z","abstract_excerpt":"Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch remains a challenge in this area, where the domain of the pre-training data might differ from that of the downstream labeled data used for fine-tuning. In multilingual tasks such as SLID, the pre-trained speech model may not support all the languages in the downstream task. To address this challenge, we propose self-supervised adaptive pre-training (SAPT) to"},"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":"2312.07338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T14:58:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1e4cf03c022b15957c7bf6eb9bfe03ece775b4a2328fba5f889105f39070dba0","abstract_canon_sha256":"e2343d6d7b171e70b63f60d7380663844066f31b94a4ce9eb76686b50f19b847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:18.446233Z","signature_b64":"YUOPE8krdazoPPooY/S0XXf1FOadpUIWYp3t6/cQtG0vyiEdxnKW6VyvzGKLeQBZsdjoTPwE9iWbhKXBQaC2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17904fe4db06c8f395e586fb98b332f890341a779d1fa3125b0aa3db4416af4e","last_reissued_at":"2026-07-05T07:23:18.445829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:18.445829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Badr M. Abdullah, Dietrich Klakow, Mohammed Maqsood Shaik","submitted_at":"2023-12-12T14:58:08Z","abstract_excerpt":"Pre-trained Transformer-based speech models have shown striking performance when fine-tuned on various downstream tasks such as automatic speech recognition and spoken language identification (SLID). However, the problem of domain mismatch remains a challenge in this area, where the domain of the pre-training data might differ from that of the downstream labeled data used for fine-tuning. In multilingual tasks such as SLID, the pre-trained speech model may not support all the languages in the downstream task. To address this challenge, we propose self-supervised adaptive pre-training (SAPT) to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07338","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/2312.07338/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":"2312.07338","created_at":"2026-07-05T07:23:18.445890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07338v1","created_at":"2026-07-05T07:23:18.445890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07338","created_at":"2026-07-05T07:23:18.445890+00:00"},{"alias_kind":"pith_short_12","alias_value":"C6IE7ZG3A3EP","created_at":"2026-07-05T07:23:18.445890+00:00"},{"alias_kind":"pith_short_16","alias_value":"C6IE7ZG3A3EPHFPF","created_at":"2026-07-05T07:23:18.445890+00:00"},{"alias_kind":"pith_short_8","alias_value":"C6IE7ZG3","created_at":"2026-07-05T07:23:18.445890+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19940","citing_title":"Analyzing Language and Geographical Variation in Speech Representations Across 60 Indic Languages","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C","json":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C.json","graph_json":"https://pith.science/api/pith-number/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/graph.json","events_json":"https://pith.science/api/pith-number/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/events.json","paper":"https://pith.science/paper/C6IE7ZG3"},"agent_actions":{"view_html":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C","download_json":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C.json","view_paper":"https://pith.science/paper/C6IE7ZG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07338&json=true","fetch_graph":"https://pith.science/api/pith-number/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/graph.json","fetch_events":"https://pith.science/api/pith-number/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/action/storage_attestation","attest_author":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/action/author_attestation","sign_citation":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/action/citation_signature","submit_replication":"https://pith.science/pith/C6IE7ZG3A3EPHFPFQ35ZRMZS7C/action/replication_record"}},"created_at":"2026-07-05T07:23:18.445890+00:00","updated_at":"2026-07-05T07:23:18.445890+00:00"}