{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TGC6ULFIDLGKWFXJT7N3KHC4GQ","short_pith_number":"pith:TGC6ULFI","schema_version":"1.0","canonical_sha256":"9985ea2ca81accab16e99fdbb51c5c3407c744cd4b2762eb9995be7895789ea1","source":{"kind":"arxiv","id":"2410.03734","version":1},"attestation_state":"computed","paper":{"title":"Accent conversion using discrete units with parallel data synthesized from controllable accented TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Waibel, Ngoc Quan Pham, Tuan Nam Nguyen","submitted_at":"2024-09-30T19:52:10Z","abstract_excerpt":"The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used one-to-one systems that could only be trained for each non-native accent. This paper presents a promising AC model that can convert many accents into native to overcome these issues. Our approach utilizes discrete units, derived from clustering self-supervised representations of native speech, as an intermediary target for accent conversion. Leveraging multi-speaker "},"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":"2410.03734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-30T19:52:10Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c5c7a6563d8548add50c6020cba897d3f2f93e768a197d377265b161a9ac08bb","abstract_canon_sha256":"d3afb6d152cbc210ca7e7a17073937dc4ae6991526c750e440a76f9147816d5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:24.105948Z","signature_b64":"n6+YjRMUsx707u2dFhfRIoBErtE21GyjwciOOd6aAwfhsgwSd1D1/SuAi+COgKEWhB6RtITbaGlq7nadk/PpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9985ea2ca81accab16e99fdbb51c5c3407c744cd4b2762eb9995be7895789ea1","last_reissued_at":"2026-07-05T09:16:24.105471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:24.105471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accent conversion using discrete units with parallel data synthesized from controllable accented TTS","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Waibel, Ngoc Quan Pham, Tuan Nam Nguyen","submitted_at":"2024-09-30T19:52:10Z","abstract_excerpt":"The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used one-to-one systems that could only be trained for each non-native accent. This paper presents a promising AC model that can convert many accents into native to overcome these issues. Our approach utilizes discrete units, derived from clustering self-supervised representations of native speech, as an intermediary target for accent conversion. Leveraging multi-speaker "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03734","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/2410.03734/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":"2410.03734","created_at":"2026-07-05T09:16:24.105529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03734v1","created_at":"2026-07-05T09:16:24.105529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03734","created_at":"2026-07-05T09:16:24.105529+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGC6ULFIDLGK","created_at":"2026-07-05T09:16:24.105529+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGC6ULFIDLGKWFXJ","created_at":"2026-07-05T09:16:24.105529+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGC6ULFI","created_at":"2026-07-05T09:16:24.105529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ","json":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ.json","graph_json":"https://pith.science/api/pith-number/TGC6ULFIDLGKWFXJT7N3KHC4GQ/graph.json","events_json":"https://pith.science/api/pith-number/TGC6ULFIDLGKWFXJT7N3KHC4GQ/events.json","paper":"https://pith.science/paper/TGC6ULFI"},"agent_actions":{"view_html":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ","download_json":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ.json","view_paper":"https://pith.science/paper/TGC6ULFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03734&json=true","fetch_graph":"https://pith.science/api/pith-number/TGC6ULFIDLGKWFXJT7N3KHC4GQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TGC6ULFIDLGKWFXJT7N3KHC4GQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ/action/storage_attestation","attest_author":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ/action/author_attestation","sign_citation":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ/action/citation_signature","submit_replication":"https://pith.science/pith/TGC6ULFIDLGKWFXJT7N3KHC4GQ/action/replication_record"}},"created_at":"2026-07-05T09:16:24.105529+00:00","updated_at":"2026-07-05T09:16:24.105529+00:00"}