{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AQBIDCFYPPPLQZBTQ6XJCKX4EC","short_pith_number":"pith:AQBIDCFY","schema_version":"1.0","canonical_sha256":"04028188b87bdeb8643387ae912afc2086be8d1d28a0be4c0d70d5dcf29c4b6d","source":{"kind":"arxiv","id":"2406.10844","version":2},"attestation_state":"computed","paper":{"title":"Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Mingyang Zhang, Xuehao Zhou, Yi Zhou, Zhizheng Wu","submitted_at":"2024-06-16T08:34:22Z","abstract_excerpt":"Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS) systems is challenging due to the complex variations of accents and the inherent entanglement between speaker and accent identities. In this paper, we propose a novel approach for multi-speaker multi-accent TTS synthesis that aims to synthesize speech for multiple speakers, each with various accents. Our approach employs a multi-scale accent modeling strategy to"},"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":"2406.10844","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-16T08:34:22Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"2c08bc74cec68f91f70a0f0b91bcaa6416640359de71b52e2f1cfd82c9547990","abstract_canon_sha256":"2a2bf91ca801031063adeca942a4361df028f50c8921d70c648f83f3766a609b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:57.885508Z","signature_b64":"998AKj1jd4AJWkCuYWlBnLwDAVwW3it+XwJpEPzONHzNWO8uNIWfjX3LbrruhFaKXZIeZtSM8jwvsURqUiG8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04028188b87bdeb8643387ae912afc2086be8d1d28a0be4c0d70d5dcf29c4b6d","last_reissued_at":"2026-07-05T09:55:57.885048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:57.885048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale Accent Modeling and Disentangling for Multi-Speaker Multi-Accent Text-to-Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Mingyang Zhang, Xuehao Zhou, Yi Zhou, Zhizheng Wu","submitted_at":"2024-06-16T08:34:22Z","abstract_excerpt":"Generating speech across different accents while preserving speaker identity is crucial for various real-world applications. However, accurately and independently modeling both speaker and accent characteristics in text-to-speech (TTS) systems is challenging due to the complex variations of accents and the inherent entanglement between speaker and accent identities. In this paper, we propose a novel approach for multi-speaker multi-accent TTS synthesis that aims to synthesize speech for multiple speakers, each with various accents. Our approach employs a multi-scale accent modeling strategy to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10844","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/2406.10844/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":"2406.10844","created_at":"2026-07-05T09:55:57.885106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10844v2","created_at":"2026-07-05T09:55:57.885106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10844","created_at":"2026-07-05T09:55:57.885106+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQBIDCFYPPPL","created_at":"2026-07-05T09:55:57.885106+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQBIDCFYPPPLQZBT","created_at":"2026-07-05T09:55:57.885106+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQBIDCFY","created_at":"2026-07-05T09:55:57.885106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27281","citing_title":"Accent Conversion: A Problem-Driven Survey of Sociolinguistic and Technical Constraints","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27273","citing_title":"Few-Shot Synthetic Accented Speech for ASR Fine-Tuning: What Helps and When?","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC","json":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC.json","graph_json":"https://pith.science/api/pith-number/AQBIDCFYPPPLQZBTQ6XJCKX4EC/graph.json","events_json":"https://pith.science/api/pith-number/AQBIDCFYPPPLQZBTQ6XJCKX4EC/events.json","paper":"https://pith.science/paper/AQBIDCFY"},"agent_actions":{"view_html":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC","download_json":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC.json","view_paper":"https://pith.science/paper/AQBIDCFY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10844&json=true","fetch_graph":"https://pith.science/api/pith-number/AQBIDCFYPPPLQZBTQ6XJCKX4EC/graph.json","fetch_events":"https://pith.science/api/pith-number/AQBIDCFYPPPLQZBTQ6XJCKX4EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC/action/storage_attestation","attest_author":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC/action/author_attestation","sign_citation":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC/action/citation_signature","submit_replication":"https://pith.science/pith/AQBIDCFYPPPLQZBTQ6XJCKX4EC/action/replication_record"}},"created_at":"2026-07-05T09:55:57.885106+00:00","updated_at":"2026-07-05T09:55:57.885106+00:00"}