{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FOZUZ654A2IZOXQD6V2RXWRXYA","short_pith_number":"pith:FOZUZ654","schema_version":"1.0","canonical_sha256":"2bb34cfbbc0691975e03f5751bda37c024030264723fff5e28fe484f20e7cc16","source":{"kind":"arxiv","id":"2607.15755","version":1},"attestation_state":"computed","paper":{"title":"AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Aruukhan, Haizhou Li, Rui Liu, Yuan Zhao, Zhenqi Jia","submitted_at":"2026-07-17T08:47:58Z","abstract_excerpt":"Conversational Speech Synthesis (CSS) aims to synthesize speech with human-like emotional expression and contextual consistency in user-agent interactions. Existing CSS methods struggle to render authentic human emotions due to limited predefined emotion label spaces (e.g., seven emotion categories), while redundant multimodal tokens in multi-turn dialogue history interfere with context understanding. To address these issues, we propose AuEmoChat, a CSS framework for authentic emotion understanding and rendering. First, we develop AuEmoCodec, which learns a discrete authentic emotion token spa"},"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":"2607.15755","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-17T08:47:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73fcf3be0ddf43728305c3a111be60e1f4f59c6ad139569cd3ce2b8231d44083","abstract_canon_sha256":"85c80ba359033a177fc1b3ee2365aa37997e8da263575f85558382cf4161ab2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:19:08.048829Z","signature_b64":"TzT85ly1QCuOdp0gp51IMj6qQmr2etCHuVtmCNKf3nqwsmwG+aP01Hbti3xfJQC8TrX2u+Ciu6hTcmPJGO18CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bb34cfbbc0691975e03f5751bda37c024030264723fff5e28fe484f20e7cc16","last_reissued_at":"2026-07-20T01:19:08.047948Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:19:08.047948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AuEmoChat: Authentic Emotion Understanding and Rendering for Conversational Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Aruukhan, Haizhou Li, Rui Liu, Yuan Zhao, Zhenqi Jia","submitted_at":"2026-07-17T08:47:58Z","abstract_excerpt":"Conversational Speech Synthesis (CSS) aims to synthesize speech with human-like emotional expression and contextual consistency in user-agent interactions. Existing CSS methods struggle to render authentic human emotions due to limited predefined emotion label spaces (e.g., seven emotion categories), while redundant multimodal tokens in multi-turn dialogue history interfere with context understanding. To address these issues, we propose AuEmoChat, a CSS framework for authentic emotion understanding and rendering. First, we develop AuEmoCodec, which learns a discrete authentic emotion token spa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15755","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/2607.15755/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":"2607.15755","created_at":"2026-07-20T01:19:08.048401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15755v1","created_at":"2026-07-20T01:19:08.048401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15755","created_at":"2026-07-20T01:19:08.048401+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOZUZ654A2IZ","created_at":"2026-07-20T01:19:08.048401+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOZUZ654A2IZOXQD","created_at":"2026-07-20T01:19:08.048401+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOZUZ654","created_at":"2026-07-20T01:19:08.048401+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/FOZUZ654A2IZOXQD6V2RXWRXYA","json":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA.json","graph_json":"https://pith.science/api/pith-number/FOZUZ654A2IZOXQD6V2RXWRXYA/graph.json","events_json":"https://pith.science/api/pith-number/FOZUZ654A2IZOXQD6V2RXWRXYA/events.json","paper":"https://pith.science/paper/FOZUZ654"},"agent_actions":{"view_html":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA","download_json":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA.json","view_paper":"https://pith.science/paper/FOZUZ654","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15755&json=true","fetch_graph":"https://pith.science/api/pith-number/FOZUZ654A2IZOXQD6V2RXWRXYA/graph.json","fetch_events":"https://pith.science/api/pith-number/FOZUZ654A2IZOXQD6V2RXWRXYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA/action/storage_attestation","attest_author":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA/action/author_attestation","sign_citation":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA/action/citation_signature","submit_replication":"https://pith.science/pith/FOZUZ654A2IZOXQD6V2RXWRXYA/action/replication_record"}},"created_at":"2026-07-20T01:19:08.048401+00:00","updated_at":"2026-07-20T01:19:08.048401+00:00"}