{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MNROKFRC62XDFTLZ326EYEAPZ5","short_pith_number":"pith:MNROKFRC","schema_version":"1.0","canonical_sha256":"6362e51622f6ae32cd79debc4c100fcf664dcc39622d4dd57e35d6d356aed165","source":{"kind":"arxiv","id":"2506.04364","version":1},"attestation_state":"computed","paper":{"title":"Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jean Maillard, Michael Auli, Vineel Pratap, Zheng-Xin Yong","submitted_at":"2025-06-04T18:23:08Z","abstract_excerpt":"To build an automatic speech recognition (ASR) system that can serve everyone in the world, the ASR needs to be robust to a wide range of accents including unseen accents. We systematically study how three different variables in training data -- the number of speakers, the audio duration per each individual speaker, and the diversity of accents -- affect ASR robustness towards unseen accents in a low-resource training regime. We observe that for a fixed number of ASR training hours, it is more beneficial to increase the number of speakers (which means each speaker contributes less) than the nu"},"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":"2506.04364","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T18:23:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4d321236d824d90958c75236bb51bb334ac22792bd00131717cc6475282462d8","abstract_canon_sha256":"9e5d4da6bba3af3c41a28b5580fa94c0fd7aadb3d7f89a0598ad47498244e1ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:13.342966Z","signature_b64":"A+Ef7slNWApt+1I7XMQ6ip6q8v3TZn1J8udvBrbHmg+HhEZWfbzNQk43UM7M2/sKfqGlADOh88cEqoU3FJyYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6362e51622f6ae32cd79debc4c100fcf664dcc39622d4dd57e35d6d356aed165","last_reissued_at":"2026-07-05T11:16:13.342520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:13.342520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jean Maillard, Michael Auli, Vineel Pratap, Zheng-Xin Yong","submitted_at":"2025-06-04T18:23:08Z","abstract_excerpt":"To build an automatic speech recognition (ASR) system that can serve everyone in the world, the ASR needs to be robust to a wide range of accents including unseen accents. We systematically study how three different variables in training data -- the number of speakers, the audio duration per each individual speaker, and the diversity of accents -- affect ASR robustness towards unseen accents in a low-resource training regime. We observe that for a fixed number of ASR training hours, it is more beneficial to increase the number of speakers (which means each speaker contributes less) than the nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04364","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/2506.04364/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":"2506.04364","created_at":"2026-07-05T11:16:13.342573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04364v1","created_at":"2026-07-05T11:16:13.342573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04364","created_at":"2026-07-05T11:16:13.342573+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNROKFRC62XD","created_at":"2026-07-05T11:16:13.342573+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNROKFRC62XDFTLZ","created_at":"2026-07-05T11:16:13.342573+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNROKFRC","created_at":"2026-07-05T11:16:13.342573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04364","citing_title":"Effects of Speaker Count, Duration, and Accent Diversity on Zero-Shot Accent Robustness in Low-Resource ASR","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5","json":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5.json","graph_json":"https://pith.science/api/pith-number/MNROKFRC62XDFTLZ326EYEAPZ5/graph.json","events_json":"https://pith.science/api/pith-number/MNROKFRC62XDFTLZ326EYEAPZ5/events.json","paper":"https://pith.science/paper/MNROKFRC"},"agent_actions":{"view_html":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5","download_json":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5.json","view_paper":"https://pith.science/paper/MNROKFRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04364&json=true","fetch_graph":"https://pith.science/api/pith-number/MNROKFRC62XDFTLZ326EYEAPZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/MNROKFRC62XDFTLZ326EYEAPZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5/action/storage_attestation","attest_author":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5/action/author_attestation","sign_citation":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5/action/citation_signature","submit_replication":"https://pith.science/pith/MNROKFRC62XDFTLZ326EYEAPZ5/action/replication_record"}},"created_at":"2026-07-05T11:16:13.342573+00:00","updated_at":"2026-07-05T11:16:13.342573+00:00"}