{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZAMWZGAWJFVLFRUP2XAKYXTYI4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ce70293da4a06696fd08e05bd97a2f3e2ed8173645df82dceb84f520c1590b93","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T01:32:44Z","title_canon_sha256":"d6ed4ce687717da265c60437849a4c5858d47fb28f792b902ef956e03835f971"},"schema_version":"1.0","source":{"id":"2501.04904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04904","created_at":"2026-07-05T09:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04904v1","created_at":"2026-07-05T09:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04904","created_at":"2026-07-05T09:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"ZAMWZGAWJFVL","created_at":"2026-07-05T09:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"ZAMWZGAWJFVLFRUP","created_at":"2026-07-05T09:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"ZAMWZGAW","created_at":"2026-07-05T09:58:48Z"}],"graph_snapshots":[{"event_id":"sha256:cd0b90f6ab30d7cb27ed7494b284233d63129efc8bbbdf5c3805eaeacddf588d","target":"graph","created_at":"2026-07-05T09:58:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.04904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, there has been a growing demand for conversational speech synthesis (CSS) that generates more natural speech by considering the conversational context. To address this, we introduce JELLY, a novel CSS framework that integrates emotion recognition and context reasoning for generating appropriate speech in conversation by fine-tuning a large language model (LLM) with multiple partial LoRA modules. We propose an Emotion-aware Q-former encoder, which enables the LLM to perceive emotions in speech. The encoder is trained to align speech emotions with text, utilizing datasets of emotional ","authors_text":"Hyung-Seok Oh, Jun-Hyeok Cha, Seong-Whan Lee, Seung-Bin Kim","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T01:32:44Z","title":"JELLY: Joint Emotion Recognition and Context Reasoning with LLMs for Conversational Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04904","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:913dc37efa1b16e972240e42c99637a2658823a60c726501ee56602e7593691f","target":"record","created_at":"2026-07-05T09:58:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ce70293da4a06696fd08e05bd97a2f3e2ed8173645df82dceb84f520c1590b93","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T01:32:44Z","title_canon_sha256":"d6ed4ce687717da265c60437849a4c5858d47fb28f792b902ef956e03835f971"},"schema_version":"1.0","source":{"id":"2501.04904","kind":"arxiv","version":1}},"canonical_sha256":"c8196c9816496ab2c68fd5c0ac5e7847154c5d4546fcd6b4679cdba4f1be1403","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8196c9816496ab2c68fd5c0ac5e7847154c5d4546fcd6b4679cdba4f1be1403","first_computed_at":"2026-07-05T09:58:48.263054Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:48.263054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CEVMgSLg0j+LMUDE0x8IRLuw9MmLh1hf8c3kUWNtJvCspZg4Z2jK6tQta0t3htq58loGtCzvaZcN7vffHZGUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:48.263466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:913dc37efa1b16e972240e42c99637a2658823a60c726501ee56602e7593691f","sha256:cd0b90f6ab30d7cb27ed7494b284233d63129efc8bbbdf5c3805eaeacddf588d"],"state_sha256":"e0938b2c526cb6b58d1969c2cf2e6ad856c243ce9e2476628883aab7f0fe8a86"}