{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C2CDIVMYUY7LLRCTSM6H46RVOP","short_pith_number":"pith:C2CDIVMY","schema_version":"1.0","canonical_sha256":"1684345598a63eb5c453933c7e7a3573cc095cca62a608b72c5fe0fbe05ba855","source":{"kind":"arxiv","id":"2303.00802","version":1},"attestation_state":"computed","paper":{"title":"Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Irina-Elena Veliche, Jilong Wu, Leda Sar{\\i}, Philipp Klumpp, Pooja Chitkara, Prashant Serai, Qing He, Rongqing Huang","submitted_at":"2023-03-01T20:05:19Z","abstract_excerpt":"The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an accent-conversion model (ACM) which transforms native US-English speech into accented pronunciation. We include phonetic knowledge in the ACM training to provide accurate feedback about how well certain pronunciation patterns were recovered in the synthesized waveform. Furthermore, we investigate the feasibility of learned accent representations instead of static embe"},"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":"2303.00802","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-01T20:05:19Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4df03fc5242b83d84dcd190916f39cdf4be129f6e573246b4dffc745e7682723","abstract_canon_sha256":"34788f8d11c0c0b31d8231536d8d4113a46109ee8442cf218e42232a28ca27cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:22.869424Z","signature_b64":"q/W9maXRt4FwGhmkiVHCxjljlL1W9yWMI1XwZuSaQgCbi+CkAHCJLAA7cLaIAbtOBeBYG01RU46LD8R0MzbZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1684345598a63eb5c453933c7e7a3573cc095cca62a608b72c5fe0fbe05ba855","last_reissued_at":"2026-07-05T05:47:22.868921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:22.868921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Irina-Elena Veliche, Jilong Wu, Leda Sar{\\i}, Philipp Klumpp, Pooja Chitkara, Prashant Serai, Qing He, Rongqing Huang","submitted_at":"2023-03-01T20:05:19Z","abstract_excerpt":"The awareness for biased ASR datasets or models has increased notably in recent years. Even for English, despite a vast amount of available training data, systems perform worse for non-native speakers. In this work, we improve an accent-conversion model (ACM) which transforms native US-English speech into accented pronunciation. We include phonetic knowledge in the ACM training to provide accurate feedback about how well certain pronunciation patterns were recovered in the synthesized waveform. Furthermore, we investigate the feasibility of learned accent representations instead of static embe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00802","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/2303.00802/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":"2303.00802","created_at":"2026-07-05T05:47:22.868977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00802v1","created_at":"2026-07-05T05:47:22.868977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00802","created_at":"2026-07-05T05:47:22.868977+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2CDIVMYUY7L","created_at":"2026-07-05T05:47:22.868977+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2CDIVMYUY7LLRCT","created_at":"2026-07-05T05:47:22.868977+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2CDIVMY","created_at":"2026-07-05T05:47:22.868977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27273","citing_title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP","json":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP.json","graph_json":"https://pith.science/api/pith-number/C2CDIVMYUY7LLRCTSM6H46RVOP/graph.json","events_json":"https://pith.science/api/pith-number/C2CDIVMYUY7LLRCTSM6H46RVOP/events.json","paper":"https://pith.science/paper/C2CDIVMY"},"agent_actions":{"view_html":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP","download_json":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP.json","view_paper":"https://pith.science/paper/C2CDIVMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00802&json=true","fetch_graph":"https://pith.science/api/pith-number/C2CDIVMYUY7LLRCTSM6H46RVOP/graph.json","fetch_events":"https://pith.science/api/pith-number/C2CDIVMYUY7LLRCTSM6H46RVOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP/action/storage_attestation","attest_author":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP/action/author_attestation","sign_citation":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP/action/citation_signature","submit_replication":"https://pith.science/pith/C2CDIVMYUY7LLRCTSM6H46RVOP/action/replication_record"}},"created_at":"2026-07-05T05:47:22.868977+00:00","updated_at":"2026-07-05T05:47:22.868977+00:00"}