{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SRR35JHZF62JFD3LQIYUR6O3UO","short_pith_number":"pith:SRR35JHZ","schema_version":"1.0","canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","source":{"kind":"arxiv","id":"2106.06233","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Chenyi Li, Dan Su, Helen Meng, Jingbei Li, Yi Meng, Zhiyong Wu","submitted_at":"2021-06-11T08:33:52Z","abstract_excerpt":"Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods in conversational TTS only model the textual information in context with a recurrent neural network (RNN). Such methods have limited ability in modeling the inter-speaker influence in conversations, and also neglect the speaking styles and the intra-speaker inertia inside each speaker. Inspired by DialogueGCN and its superiority in modeling such conversation"},"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":"2106.06233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T08:33:52Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c1935094d142719721266cef022c3c7db48e89c6ed2f8a213d56f0bf5dd8c740","abstract_canon_sha256":"8ee52cabab10ee5803d4b8106634efced2177e565a856c2009f6da784e63be18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:22.676618Z","signature_b64":"9npVJD6zq1zsfF22xR5lY/R+7ZDk5oXVfVWIdDH0Zr2pVldqKRUGXS3IwcKjTe1pBXmSwCkHGdpCkQUHeXRsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","last_reissued_at":"2026-07-05T04:10:22.676117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:22.676117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Chenyi Li, Dan Su, Helen Meng, Jingbei Li, Yi Meng, Zhiyong Wu","submitted_at":"2021-06-11T08:33:52Z","abstract_excerpt":"Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods in conversational TTS only model the textual information in context with a recurrent neural network (RNN). Such methods have limited ability in modeling the inter-speaker influence in conversations, and also neglect the speaking styles and the intra-speaker inertia inside each speaker. Inspired by DialogueGCN and its superiority in modeling such conversation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06233","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/2106.06233/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":"2106.06233","created_at":"2026-07-05T04:10:22.676184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06233v2","created_at":"2026-07-05T04:10:22.676184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06233","created_at":"2026-07-05T04:10:22.676184+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRR35JHZF62J","created_at":"2026-07-05T04:10:22.676184+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRR35JHZF62JFD3L","created_at":"2026-07-05T04:10:22.676184+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRR35JHZ","created_at":"2026-07-05T04:10:22.676184+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/SRR35JHZF62JFD3LQIYUR6O3UO","json":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO.json","graph_json":"https://pith.science/api/pith-number/SRR35JHZF62JFD3LQIYUR6O3UO/graph.json","events_json":"https://pith.science/api/pith-number/SRR35JHZF62JFD3LQIYUR6O3UO/events.json","paper":"https://pith.science/paper/SRR35JHZ"},"agent_actions":{"view_html":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO","download_json":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO.json","view_paper":"https://pith.science/paper/SRR35JHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06233&json=true","fetch_graph":"https://pith.science/api/pith-number/SRR35JHZF62JFD3LQIYUR6O3UO/graph.json","fetch_events":"https://pith.science/api/pith-number/SRR35JHZF62JFD3LQIYUR6O3UO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/action/storage_attestation","attest_author":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/action/author_attestation","sign_citation":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/action/citation_signature","submit_replication":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/action/replication_record"}},"created_at":"2026-07-05T04:10:22.676184+00:00","updated_at":"2026-07-05T04:10:22.676184+00:00"}