{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZAMWZGAWJFVLFRUP2XAKYXTYI4","short_pith_number":"pith:ZAMWZGAW","canonical_record":{"source":{"id":"2501.04904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T01:32:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d6ed4ce687717da265c60437849a4c5858d47fb28f792b902ef956e03835f971","abstract_canon_sha256":"ce70293da4a06696fd08e05bd97a2f3e2ed8173645df82dceb84f520c1590b93"},"schema_version":"1.0"},"canonical_sha256":"c8196c9816496ab2c68fd5c0ac5e7847154c5d4546fcd6b4679cdba4f1be1403","source":{"kind":"arxiv","id":"2501.04904","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZAMWZGAWJFVLFRUP2XAKYXTYI4","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T01:32:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d6ed4ce687717da265c60437849a4c5858d47fb28f792b902ef956e03835f971","abstract_canon_sha256":"ce70293da4a06696fd08e05bd97a2f3e2ed8173645df82dceb84f520c1590b93"},"schema_version":"1.0"},"canonical_sha256":"c8196c9816496ab2c68fd5c0ac5e7847154c5d4546fcd6b4679cdba4f1be1403","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:48.263466Z","signature_b64":"CEVMgSLg0j+LMUDE0x8IRLuw9MmLh1hf8c3kUWNtJvCspZg4Z2jK6tQta0t3htq58loGtCzvaZcN7vffHZGUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8196c9816496ab2c68fd5c0ac5e7847154c5d4546fcd6b4679cdba4f1be1403","last_reissued_at":"2026-07-05T09:58:48.263054Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:48.263054Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04904","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wlq8IeO1/ypsfF8jJIZNb0Xk1WyAYNldPUH5qXQBIE1gtLnco1dVQ5c5RiDUwlGqCH5WZVUHcNgJSELDMl5IDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:48:02.699153Z"},"content_sha256":"913dc37efa1b16e972240e42c99637a2658823a60c726501ee56602e7593691f","schema_version":"1.0","event_id":"sha256:913dc37efa1b16e972240e42c99637a2658823a60c726501ee56602e7593691f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZAMWZGAWJFVLFRUP2XAKYXTYI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JELLY: Joint Emotion Recognition and Context Reasoning with LLMs for Conversational Speech Synthesis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Hyung-Seok Oh, Jun-Hyeok Cha, Seong-Whan Lee, Seung-Bin Kim","submitted_at":"2025-01-09T01:32:44Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04904","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/2501.04904/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:58:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4OJS00mw951T8Zw0PXvmOLbFAxV3WAAuwsFws7++VmS+FKbrwaTiQ3DUwt2Mrmu3Igv1a4Wva3JMmDRO2SkfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T11:48:02.699662Z"},"content_sha256":"cd0b90f6ab30d7cb27ed7494b284233d63129efc8bbbdf5c3805eaeacddf588d","schema_version":"1.0","event_id":"sha256:cd0b90f6ab30d7cb27ed7494b284233d63129efc8bbbdf5c3805eaeacddf588d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/bundle.json","state_url":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T11:48:02Z","links":{"resolver":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4","bundle":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/bundle.json","state":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SnicoTd8ZoqxvVYD0OqI6xozv/fxg6OY8zoYrKVaKDDgQhaGsyFXc8+56q2l7XyaTbQR28z+ljn6bwec5j+BCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T11:48:02.705031Z","bundle_sha256":"95f53903ae206c2d365c45975ba0ab1bdd4c149c82c7d4dad0e305f28cda8692"}}