{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7N64U3D4ZPTEYIU66JJ2KTQ3I3","short_pith_number":"pith:7N64U3D4","schema_version":"1.0","canonical_sha256":"fb7dca6c7ccbe64c229ef253a54e1b46d285e5cff6a2236b73a214639fc5ee6b","source":{"kind":"arxiv","id":"2312.16850","version":2},"attestation_state":"computed","paper":{"title":"Accent-VITS:accent transfer for end-to-end TTS","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Linhan Ma, Pengcheng Zhu, Xinfa Zhu, Yi Lei, Yongmao Zhang, Ziqian Ning","submitted_at":"2023-12-28T06:37:52Z","abstract_excerpt":"Accent transfer aims to transfer an accent from a source speaker to synthetic speech in the target speaker's voice. The main challenge is how to effectively disentangle speaker timbre and accent which are entangled in speech. This paper presents a VITS-based end-to-end accent transfer model named Accent-VITS.Based on the main structure of VITS, Accent-VITS makes substantial improvements to enable effective and stable accent transfer.We leverage a hierarchical CVAE structure to model accent pronunciation information and acoustic features, respectively, using bottleneck features and mel spectrum"},"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":"2312.16850","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-28T06:37:52Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d6d9065ba4fb1ab5a33f1638a1e25c3e9783d123179bd8e02a9b55f44b0cf82b","abstract_canon_sha256":"6870305a4a3cf246b1b43c7f1075465e39391eebdebca25d18c6fa4a81b011ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:48.304347Z","signature_b64":"YQ+4IaRRp1+Ek4uh04pVRWD7EyPJ6jbnN69F39940gzJJ2fXNAtRlcvqSBa1um8IAcU7bFQlaYqLjKHaflr7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb7dca6c7ccbe64c229ef253a54e1b46d285e5cff6a2236b73a214639fc5ee6b","last_reissued_at":"2026-07-05T07:28:48.303846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:48.303846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accent-VITS:accent transfer for end-to-end TTS","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Linhan Ma, Pengcheng Zhu, Xinfa Zhu, Yi Lei, Yongmao Zhang, Ziqian Ning","submitted_at":"2023-12-28T06:37:52Z","abstract_excerpt":"Accent transfer aims to transfer an accent from a source speaker to synthetic speech in the target speaker's voice. The main challenge is how to effectively disentangle speaker timbre and accent which are entangled in speech. This paper presents a VITS-based end-to-end accent transfer model named Accent-VITS.Based on the main structure of VITS, Accent-VITS makes substantial improvements to enable effective and stable accent transfer.We leverage a hierarchical CVAE structure to model accent pronunciation information and acoustic features, respectively, using bottleneck features and mel spectrum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16850","kind":"arxiv","version":2},"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/2312.16850/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":"2312.16850","created_at":"2026-07-05T07:28:48.303921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16850v2","created_at":"2026-07-05T07:28:48.303921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16850","created_at":"2026-07-05T07:28:48.303921+00:00"},{"alias_kind":"pith_short_12","alias_value":"7N64U3D4ZPTE","created_at":"2026-07-05T07:28:48.303921+00:00"},{"alias_kind":"pith_short_16","alias_value":"7N64U3D4ZPTEYIU6","created_at":"2026-07-05T07:28:48.303921+00:00"},{"alias_kind":"pith_short_8","alias_value":"7N64U3D4","created_at":"2026-07-05T07:28:48.303921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16417","citing_title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3","json":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3.json","graph_json":"https://pith.science/api/pith-number/7N64U3D4ZPTEYIU66JJ2KTQ3I3/graph.json","events_json":"https://pith.science/api/pith-number/7N64U3D4ZPTEYIU66JJ2KTQ3I3/events.json","paper":"https://pith.science/paper/7N64U3D4"},"agent_actions":{"view_html":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3","download_json":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3.json","view_paper":"https://pith.science/paper/7N64U3D4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16850&json=true","fetch_graph":"https://pith.science/api/pith-number/7N64U3D4ZPTEYIU66JJ2KTQ3I3/graph.json","fetch_events":"https://pith.science/api/pith-number/7N64U3D4ZPTEYIU66JJ2KTQ3I3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3/action/storage_attestation","attest_author":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3/action/author_attestation","sign_citation":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3/action/citation_signature","submit_replication":"https://pith.science/pith/7N64U3D4ZPTEYIU66JJ2KTQ3I3/action/replication_record"}},"created_at":"2026-07-05T07:28:48.303921+00:00","updated_at":"2026-07-05T07:28:48.303921+00:00"}