{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NENVRADCSUCY3GIGGR6GU7MRIM","short_pith_number":"pith:NENVRADC","schema_version":"1.0","canonical_sha256":"691b58806295058d9906347c6a7d9143026c7e9e23aa2a31a991125f55b57dbc","source":{"kind":"arxiv","id":"2312.10358","version":1},"attestation_state":"computed","paper":{"title":"CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Dengfeng Ke, Fengping Wang, Jinlong Xue, Qifei Li, Ya Li, Yayue Deng, Yichen Han, Yingming Gao, Yukang Jia","submitted_at":"2023-12-16T07:05:16Z","abstract_excerpt":"Conversational speech synthesis (CSS) incorporates historical dialogue as supplementary information with the aim of generating speech that has dialogue-appropriate prosody. While previous methods have already delved into enhancing context comprehension, context representation still lacks effective representation capabilities and context-sensitive discriminability. In this paper, we introduce a contrastive learning-based CSS framework, CONCSS. Within this framework, we define an innovative pretext task specific to CSS that enables the model to perform self-supervised learning on unlabeled conve"},"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":"2312.10358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-16T07:05:16Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"3e825f0043d54c4b4f5924f5a263c53d37506d7bc9050e63caf6e93f5f00948e","abstract_canon_sha256":"1edf06a8a7e939f8caa7e0520fb9301c5b6b024ae7c012cb144ac6a4f5d2e3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:05.467648Z","signature_b64":"TfiQc+mQeUfIMGCYqxP9+GtJ4Ssbf9Vq6rpz1iDor3hAtUcWcYarOi+Q0LmAto/whvjlkKcskR1oRE6fVm1RCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"691b58806295058d9906347c6a7d9143026c7e9e23aa2a31a991125f55b57dbc","last_reissued_at":"2026-07-05T07:25:05.467144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:05.467144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CONCSS: Contrastive-based Context Comprehension for Dialogue-appropriate Prosody in Conversational Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.CL","authors_text":"Dengfeng Ke, Fengping Wang, Jinlong Xue, Qifei Li, Ya Li, Yayue Deng, Yichen Han, Yingming Gao, Yukang Jia","submitted_at":"2023-12-16T07:05:16Z","abstract_excerpt":"Conversational speech synthesis (CSS) incorporates historical dialogue as supplementary information with the aim of generating speech that has dialogue-appropriate prosody. While previous methods have already delved into enhancing context comprehension, context representation still lacks effective representation capabilities and context-sensitive discriminability. In this paper, we introduce a contrastive learning-based CSS framework, CONCSS. Within this framework, we define an innovative pretext task specific to CSS that enables the model to perform self-supervised learning on unlabeled conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10358","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/2312.10358/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":"2312.10358","created_at":"2026-07-05T07:25:05.467203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10358v1","created_at":"2026-07-05T07:25:05.467203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10358","created_at":"2026-07-05T07:25:05.467203+00:00"},{"alias_kind":"pith_short_12","alias_value":"NENVRADCSUCY","created_at":"2026-07-05T07:25:05.467203+00:00"},{"alias_kind":"pith_short_16","alias_value":"NENVRADCSUCY3GIG","created_at":"2026-07-05T07:25:05.467203+00:00"},{"alias_kind":"pith_short_8","alias_value":"NENVRADC","created_at":"2026-07-05T07:25:05.467203+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/NENVRADCSUCY3GIGGR6GU7MRIM","json":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM.json","graph_json":"https://pith.science/api/pith-number/NENVRADCSUCY3GIGGR6GU7MRIM/graph.json","events_json":"https://pith.science/api/pith-number/NENVRADCSUCY3GIGGR6GU7MRIM/events.json","paper":"https://pith.science/paper/NENVRADC"},"agent_actions":{"view_html":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM","download_json":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM.json","view_paper":"https://pith.science/paper/NENVRADC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10358&json=true","fetch_graph":"https://pith.science/api/pith-number/NENVRADCSUCY3GIGGR6GU7MRIM/graph.json","fetch_events":"https://pith.science/api/pith-number/NENVRADCSUCY3GIGGR6GU7MRIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM/action/storage_attestation","attest_author":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM/action/author_attestation","sign_citation":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM/action/citation_signature","submit_replication":"https://pith.science/pith/NENVRADCSUCY3GIGGR6GU7MRIM/action/replication_record"}},"created_at":"2026-07-05T07:25:05.467203+00:00","updated_at":"2026-07-05T07:25:05.467203+00:00"}