{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3Q3AX36O4BZPCEQIGF7FZG6ADS","short_pith_number":"pith:3Q3AX36O","schema_version":"1.0","canonical_sha256":"dc360befcee072f11208317e5c9bc01ca3a1105c4a544bd13e5a3cb8a8c398ff","source":{"kind":"arxiv","id":"2303.07578","version":1},"attestation_state":"computed","paper":{"title":"VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity Preservation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Akshit Arora, Boris Ginsburg, Bryan Catanzaro, Jo\\~ao Felipe Santos, Kevin J. Shih, Rafael Valle, Rohan Badlani, Subhankar Ghosh","submitted_at":"2023-03-14T01:55:41Z","abstract_excerpt":"We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained $F_0$ and energy features for speech synthesis. We utilize the Indic languages dataset, released for LIMMITS 2023 as part of ICASSP Signal Processing Grand Challenge, to synthesize speech in 3 different languages. Our model supports transferring the language of a speaker while retaining their voice and the native accent of the target language. We utilize th"},"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":"2303.07578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-03-14T01:55:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"e4cf582534d5f20377f24df5bc1878567f5eb31abbdeb38020d71187e5773677","abstract_canon_sha256":"dedf11ae11612afbe37ebcc2b6dfe3f122208ab7d570f61830b11d3036112384"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:08.157811Z","signature_b64":"5bYGGxJ++6MdgNvpKID1Ii9PHFTKqkVsK4GJdIiEyM+3+aVCNu9o7WT56/ZBMZDQrkP5u1RSu8tl5oeIxppXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc360befcee072f11208317e5c9bc01ca3a1105c4a544bd13e5a3cb8a8c398ff","last_reissued_at":"2026-07-05T05:51:08.157369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:08.157369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with Identity Preservation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Akshit Arora, Boris Ginsburg, Bryan Catanzaro, Jo\\~ao Felipe Santos, Kevin J. Shih, Rafael Valle, Rohan Badlani, Subhankar Ghosh","submitted_at":"2023-03-14T01:55:41Z","abstract_excerpt":"We introduce VANI, a very lightweight multi-lingual accent controllable speech synthesis system. Our model builds upon disentanglement strategies proposed in RADMMM and supports explicit control of accent, language, speaker and fine-grained $F_0$ and energy features for speech synthesis. We utilize the Indic languages dataset, released for LIMMITS 2023 as part of ICASSP Signal Processing Grand Challenge, to synthesize speech in 3 different languages. Our model supports transferring the language of a speaker while retaining their voice and the native accent of the target language. We utilize th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07578","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/2303.07578/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":"2303.07578","created_at":"2026-07-05T05:51:08.157433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07578v1","created_at":"2026-07-05T05:51:08.157433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07578","created_at":"2026-07-05T05:51:08.157433+00:00"},{"alias_kind":"pith_short_12","alias_value":"3Q3AX36O4BZP","created_at":"2026-07-05T05:51:08.157433+00:00"},{"alias_kind":"pith_short_16","alias_value":"3Q3AX36O4BZPCEQI","created_at":"2026-07-05T05:51:08.157433+00:00"},{"alias_kind":"pith_short_8","alias_value":"3Q3AX36O","created_at":"2026-07-05T05:51:08.157433+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/3Q3AX36O4BZPCEQIGF7FZG6ADS","json":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS.json","graph_json":"https://pith.science/api/pith-number/3Q3AX36O4BZPCEQIGF7FZG6ADS/graph.json","events_json":"https://pith.science/api/pith-number/3Q3AX36O4BZPCEQIGF7FZG6ADS/events.json","paper":"https://pith.science/paper/3Q3AX36O"},"agent_actions":{"view_html":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS","download_json":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS.json","view_paper":"https://pith.science/paper/3Q3AX36O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07578&json=true","fetch_graph":"https://pith.science/api/pith-number/3Q3AX36O4BZPCEQIGF7FZG6ADS/graph.json","fetch_events":"https://pith.science/api/pith-number/3Q3AX36O4BZPCEQIGF7FZG6ADS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS/action/storage_attestation","attest_author":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS/action/author_attestation","sign_citation":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS/action/citation_signature","submit_replication":"https://pith.science/pith/3Q3AX36O4BZPCEQIGF7FZG6ADS/action/replication_record"}},"created_at":"2026-07-05T05:51:08.157433+00:00","updated_at":"2026-07-05T05:51:08.157433+00:00"}