{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VQYXBENWNXPEZVY57V3DTVHRMF","short_pith_number":"pith:VQYXBENW","schema_version":"1.0","canonical_sha256":"ac317091b66dde4cd71dfd7639d4f1614f3c97b6321ccf58bae906f083a0d05e","source":{"kind":"arxiv","id":"2508.14130","version":1},"attestation_state":"computed","paper":{"title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Antony Perzo, Hugo Thimonier, Renaud Seguier","submitted_at":"2025-08-19T06:58:16Z","abstract_excerpt":"Emotion recognition from speech is a challenging task that requires capturing both linguistic and paralinguistic cues, with critical applications in human-computer interaction and mental health monitoring. Recent works have highlighted the ability of Large Language Models (LLMs) to perform tasks outside of the sole natural language area. In particular, recent approaches have investigated coupling LLMs with other data modalities by using pre-trained backbones and different fusion mechanisms. This work proposes a novel approach that fine-tunes an LLM with audio and text representations for emoti"},"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":"2508.14130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-19T06:58:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a84b93b9a18a5e254bc319f83cbb019ae73bcedd0be00e3626a0581042b6a47f","abstract_canon_sha256":"3a6ef3e470283917765f13a28bff09d4293311666097432db456c467c2719304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:26.346924Z","signature_b64":"3TO+FRZBxD2ODO6IYVfEqp+lasvMNfAKuUpktBAPVoxKfciIyvbt6Q+U8g4+hRf1jRdo8cTgNUa5AXI8aCCpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac317091b66dde4cd71dfd7639d4f1614f3c97b6321ccf58bae906f083a0d05e","last_reissued_at":"2026-07-05T11:56:26.346446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:26.346446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Antony Perzo, Hugo Thimonier, Renaud Seguier","submitted_at":"2025-08-19T06:58:16Z","abstract_excerpt":"Emotion recognition from speech is a challenging task that requires capturing both linguistic and paralinguistic cues, with critical applications in human-computer interaction and mental health monitoring. Recent works have highlighted the ability of Large Language Models (LLMs) to perform tasks outside of the sole natural language area. In particular, recent approaches have investigated coupling LLMs with other data modalities by using pre-trained backbones and different fusion mechanisms. This work proposes a novel approach that fine-tunes an LLM with audio and text representations for emoti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14130","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/2508.14130/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":"2508.14130","created_at":"2026-07-05T11:56:26.346507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14130v1","created_at":"2026-07-05T11:56:26.346507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14130","created_at":"2026-07-05T11:56:26.346507+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQYXBENWNXPE","created_at":"2026-07-05T11:56:26.346507+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQYXBENWNXPEZVY5","created_at":"2026-07-05T11:56:26.346507+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQYXBENW","created_at":"2026-07-05T11:56:26.346507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24941","citing_title":"EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07571","citing_title":"A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF","json":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF.json","graph_json":"https://pith.science/api/pith-number/VQYXBENWNXPEZVY57V3DTVHRMF/graph.json","events_json":"https://pith.science/api/pith-number/VQYXBENWNXPEZVY57V3DTVHRMF/events.json","paper":"https://pith.science/paper/VQYXBENW"},"agent_actions":{"view_html":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF","download_json":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF.json","view_paper":"https://pith.science/paper/VQYXBENW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14130&json=true","fetch_graph":"https://pith.science/api/pith-number/VQYXBENWNXPEZVY57V3DTVHRMF/graph.json","fetch_events":"https://pith.science/api/pith-number/VQYXBENWNXPEZVY57V3DTVHRMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF/action/storage_attestation","attest_author":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF/action/author_attestation","sign_citation":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF/action/citation_signature","submit_replication":"https://pith.science/pith/VQYXBENWNXPEZVY57V3DTVHRMF/action/replication_record"}},"created_at":"2026-07-05T11:56:26.346507+00:00","updated_at":"2026-07-05T11:56:26.346507+00:00"}