{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2PNUYTRHZKMUE5QE3DRYJ2MKBU","short_pith_number":"pith:2PNUYTRH","schema_version":"1.0","canonical_sha256":"d3db4c4e27ca99427604d8e384e98a0d1459040daf61956b403f07487a455b2e","source":{"kind":"arxiv","id":"2508.01691","version":1},"attestation_state":"computed","paper":{"title":"Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anfeng Xu, Dani Byrd, Jihwan Lee, Kevin Huang, Shrikanth Narayanan, Thanathai Lertpetchpun, Tiantian Feng, Xuan Shi, Yoonjeong Lee","submitted_at":"2025-08-03T09:51:28Z","abstract_excerpt":"We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian. Our study used over 2 million training utterances from 30 publicly available speech corpora that are provided with dialectal information. We evaluate the performance of several widely used speech foundation models in classifying speech"},"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":"2508.01691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-08-03T09:51:28Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"f71dc4d1c0495dd3048a384b153dba252f6b87515f0553d6d71dc767f8434f24","abstract_canon_sha256":"af8eb75baf824a674309c5b452de0ebca59971d8a4ca5320b073c61ed46b0c30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:07.533170Z","signature_b64":"AQn2oaN/ud8tgJRo4Z8xD5Rwmrq2mu3jLSnpMxAe7F7L+y6/CvsfdSJQfxu/PjlKktLAhHoUiRE3mePncYnKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3db4c4e27ca99427604d8e384e98a0d1459040daf61956b403f07487a455b2e","last_reissued_at":"2026-07-05T11:48:07.532656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:07.532656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anfeng Xu, Dani Byrd, Jihwan Lee, Kevin Huang, Shrikanth Narayanan, Thanathai Lertpetchpun, Tiantian Feng, Xuan Shi, Yoonjeong Lee","submitted_at":"2025-08-03T09:51:28Z","abstract_excerpt":"We present Voxlect, a novel benchmark for modeling dialects and regional languages worldwide using speech foundation models. Specifically, we report comprehensive benchmark evaluations on dialects and regional language varieties in English, Arabic, Mandarin and Cantonese, Tibetan, Indic languages, Thai, Spanish, French, German, Brazilian Portuguese, and Italian. Our study used over 2 million training utterances from 30 publicly available speech corpora that are provided with dialectal information. We evaluate the performance of several widely used speech foundation models in classifying speech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01691","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/2508.01691/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":"2508.01691","created_at":"2026-07-05T11:48:07.532730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01691v1","created_at":"2026-07-05T11:48:07.532730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01691","created_at":"2026-07-05T11:48:07.532730+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PNUYTRHZKMU","created_at":"2026-07-05T11:48:07.532730+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PNUYTRHZKMUE5QE","created_at":"2026-07-05T11:48:07.532730+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PNUYTRH","created_at":"2026-07-05T11:48:07.532730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23578","citing_title":"Style Amnesia: Investigating Speaking Style Degradation and Mitigation in Multi-Turn Spoken Language Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU","json":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU.json","graph_json":"https://pith.science/api/pith-number/2PNUYTRHZKMUE5QE3DRYJ2MKBU/graph.json","events_json":"https://pith.science/api/pith-number/2PNUYTRHZKMUE5QE3DRYJ2MKBU/events.json","paper":"https://pith.science/paper/2PNUYTRH"},"agent_actions":{"view_html":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU","download_json":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU.json","view_paper":"https://pith.science/paper/2PNUYTRH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01691&json=true","fetch_graph":"https://pith.science/api/pith-number/2PNUYTRHZKMUE5QE3DRYJ2MKBU/graph.json","fetch_events":"https://pith.science/api/pith-number/2PNUYTRHZKMUE5QE3DRYJ2MKBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU/action/storage_attestation","attest_author":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU/action/author_attestation","sign_citation":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU/action/citation_signature","submit_replication":"https://pith.science/pith/2PNUYTRHZKMUE5QE3DRYJ2MKBU/action/replication_record"}},"created_at":"2026-07-05T11:48:07.532730+00:00","updated_at":"2026-07-05T11:48:07.532730+00:00"}