{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZAMWZGAWJFVLFRUP2XAKYXTYI4","short_pith_number":"pith:ZAMWZGAW","schema_version":"1.0","canonical_sha256":"c8196c9816496ab2c68fd5c0ac5e7847154c5d4546fcd6b4679cdba4f1be1403","source":{"kind":"arxiv","id":"2501.04904","version":1},"attestation_state":"computed","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 "},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.04904","created_at":"2026-07-05T09:58:48.263110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04904v1","created_at":"2026-07-05T09:58:48.263110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04904","created_at":"2026-07-05T09:58:48.263110+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAMWZGAWJFVL","created_at":"2026-07-05T09:58:48.263110+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAMWZGAWJFVLFRUP","created_at":"2026-07-05T09:58:48.263110+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAMWZGAW","created_at":"2026-07-05T09:58:48.263110+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/ZAMWZGAWJFVLFRUP2XAKYXTYI4","json":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4.json","graph_json":"https://pith.science/api/pith-number/ZAMWZGAWJFVLFRUP2XAKYXTYI4/graph.json","events_json":"https://pith.science/api/pith-number/ZAMWZGAWJFVLFRUP2XAKYXTYI4/events.json","paper":"https://pith.science/paper/ZAMWZGAW"},"agent_actions":{"view_html":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4","download_json":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4.json","view_paper":"https://pith.science/paper/ZAMWZGAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04904&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAMWZGAWJFVLFRUP2XAKYXTYI4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAMWZGAWJFVLFRUP2XAKYXTYI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/action/storage_attestation","attest_author":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/action/author_attestation","sign_citation":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/action/citation_signature","submit_replication":"https://pith.science/pith/ZAMWZGAWJFVLFRUP2XAKYXTYI4/action/replication_record"}},"created_at":"2026-07-05T09:58:48.263110+00:00","updated_at":"2026-07-05T09:58:48.263110+00:00"}