{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2FUL6RL3NG2CB2ZDPIIXCQV7D2","short_pith_number":"pith:2FUL6RL3","schema_version":"1.0","canonical_sha256":"d168bf457b69b420eb237a117142bf1eb1d88983b85d13e0defe7bd51cdd5b33","source":{"kind":"arxiv","id":"2312.10381","version":3},"attestation_state":"computed","paper":{"title":"SECap: Speech Emotion Captioning with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guangzhi Li, Hangting Chen, Jianwei Yu, Qiaochu Huang, Rongzhi Gu, Shixiong Zhang, Yaoxun Xu, Yi Luo, Zhiyong Wu","submitted_at":"2023-12-16T08:33:10Z","abstract_excerpt":"Speech emotions are crucial in human communication and are extensively used in fields like speech synthesis and natural language understanding. Most prior studies, such as speech emotion recognition, have categorized speech emotions into a fixed set of classes. Yet, emotions expressed in human speech are often complex, and categorizing them into predefined groups can be insufficient to adequately represent speech emotions. On the contrary, describing speech emotions directly by means of natural language may be a more effective approach. Regrettably, there are not many studies available that ha"},"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":"2312.10381","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-16T08:33:10Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"cef19c2ed0ad1578dd686abddb67424d794b8c9042740b91e71d43824b931689","abstract_canon_sha256":"3f7ea631a70de02be8848b4fd54b278ed768123453620b9964bf1f97be18bc16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:28.074462Z","signature_b64":"8cEvX8+eMJKmwJwAu5Q4cRnPv4BN2sDhnZUo4o2O/T8l9PjKlhchitD/xzhjOCFVE/nLR4O89DnM9DrMC9gECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d168bf457b69b420eb237a117142bf1eb1d88983b85d13e0defe7bd51cdd5b33","last_reissued_at":"2026-07-05T07:27:28.073961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:28.073961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SECap: Speech Emotion Captioning with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Guangzhi Li, Hangting Chen, Jianwei Yu, Qiaochu Huang, Rongzhi Gu, Shixiong Zhang, Yaoxun Xu, Yi Luo, Zhiyong Wu","submitted_at":"2023-12-16T08:33:10Z","abstract_excerpt":"Speech emotions are crucial in human communication and are extensively used in fields like speech synthesis and natural language understanding. Most prior studies, such as speech emotion recognition, have categorized speech emotions into a fixed set of classes. Yet, emotions expressed in human speech are often complex, and categorizing them into predefined groups can be insufficient to adequately represent speech emotions. On the contrary, describing speech emotions directly by means of natural language may be a more effective approach. Regrettably, there are not many studies available that ha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10381","kind":"arxiv","version":3},"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/2312.10381/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":"2312.10381","created_at":"2026-07-05T07:27:28.074026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10381v3","created_at":"2026-07-05T07:27:28.074026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10381","created_at":"2026-07-05T07:27:28.074026+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FUL6RL3NG2C","created_at":"2026-07-05T07:27:28.074026+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FUL6RL3NG2CB2ZD","created_at":"2026-07-05T07:27:28.074026+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FUL6RL3","created_at":"2026-07-05T07:27:28.074026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19950","citing_title":"AffectVerse: Emotional World Models for Multimodal Affective Computing","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2","json":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2.json","graph_json":"https://pith.science/api/pith-number/2FUL6RL3NG2CB2ZDPIIXCQV7D2/graph.json","events_json":"https://pith.science/api/pith-number/2FUL6RL3NG2CB2ZDPIIXCQV7D2/events.json","paper":"https://pith.science/paper/2FUL6RL3"},"agent_actions":{"view_html":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2","download_json":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2.json","view_paper":"https://pith.science/paper/2FUL6RL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10381&json=true","fetch_graph":"https://pith.science/api/pith-number/2FUL6RL3NG2CB2ZDPIIXCQV7D2/graph.json","fetch_events":"https://pith.science/api/pith-number/2FUL6RL3NG2CB2ZDPIIXCQV7D2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2/action/storage_attestation","attest_author":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2/action/author_attestation","sign_citation":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2/action/citation_signature","submit_replication":"https://pith.science/pith/2FUL6RL3NG2CB2ZDPIIXCQV7D2/action/replication_record"}},"created_at":"2026-07-05T07:27:28.074026+00:00","updated_at":"2026-07-05T07:27:28.074026+00:00"}