{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RKEUS4ZUGZB7OMJ7RJJRJFRXZ6","short_pith_number":"pith:RKEUS4ZU","schema_version":"1.0","canonical_sha256":"8a894973343643f7313f8a53149637cf9c258067beb76ab633cdac84e36ee48b","source":{"kind":"arxiv","id":"2506.02088","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Alef Iury Siqueira Ferreira, Alexandre Ferro Filho, Arlindo Galv\\~ao Filho, Daniel Ribeiro, Fernanda Lustosa, Frederico Santos de Oliveira, Lucas \\'Olives, Lucas Rafael Gris, Luiz Fernando, Rodrigo Tanaka","submitted_at":"2025-06-02T13:46:02Z","abstract_excerpt":"Training SER models in natural, spontaneous speech is especially challenging due to the subtle expression of emotions and the unpredictable nature of real-world audio. In this paper, we present a robust system for the INTERSPEECH 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge, focusing on categorical emotion recognition. Our method combines state-of-the-art audio models with text features enriched by prosodic and spectral cues. In particular, we investigate the effectiveness of Fundamental Frequency (F0) quantization and the use of a pretrained audio tagging model. We als"},"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":"2506.02088","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-02T13:46:02Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"6e0375a4b8f4f1b1dc2305c91dd8d63fcf7e382e819944f4c82d3f4f92acdd11","abstract_canon_sha256":"0ab62eec94e863b6e2a3133546b10f200e476da4080d7807b70cbccb955b5e1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:32.230183Z","signature_b64":"izKI2CIGA7a49AB/hVhRUAopCkPHmLQnFa2rTvmPlIoCZsos7C0oQGUZUv57v5puk1J80p4O3odxwneYLv/HAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a894973343643f7313f8a53149637cf9c258067beb76ab633cdac84e36ee48b","last_reissued_at":"2026-07-05T11:14:32.229773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:32.229773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.SD","authors_text":"Alef Iury Siqueira Ferreira, Alexandre Ferro Filho, Arlindo Galv\\~ao Filho, Daniel Ribeiro, Fernanda Lustosa, Frederico Santos de Oliveira, Lucas \\'Olives, Lucas Rafael Gris, Luiz Fernando, Rodrigo Tanaka","submitted_at":"2025-06-02T13:46:02Z","abstract_excerpt":"Training SER models in natural, spontaneous speech is especially challenging due to the subtle expression of emotions and the unpredictable nature of real-world audio. In this paper, we present a robust system for the INTERSPEECH 2025 Speech Emotion Recognition in Naturalistic Conditions Challenge, focusing on categorical emotion recognition. Our method combines state-of-the-art audio models with text features enriched by prosodic and spectral cues. In particular, we investigate the effectiveness of Fundamental Frequency (F0) quantization and the use of a pretrained audio tagging model. We als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02088","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/2506.02088/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":"2506.02088","created_at":"2026-07-05T11:14:32.229833+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02088v1","created_at":"2026-07-05T11:14:32.229833+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02088","created_at":"2026-07-05T11:14:32.229833+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKEUS4ZUGZB7","created_at":"2026-07-05T11:14:32.229833+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKEUS4ZUGZB7OMJ7","created_at":"2026-07-05T11:14:32.229833+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKEUS4ZU","created_at":"2026-07-05T11:14:32.229833+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02088","citing_title":"Enhancing Speech Emotion Recognition with Graph-Based Multimodal Fusion and Prosodic Features for the Speech Emotion Recognition in Naturalistic Conditions Challenge at Interspeech 2025","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6","json":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6.json","graph_json":"https://pith.science/api/pith-number/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/graph.json","events_json":"https://pith.science/api/pith-number/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/events.json","paper":"https://pith.science/paper/RKEUS4ZU"},"agent_actions":{"view_html":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6","download_json":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6.json","view_paper":"https://pith.science/paper/RKEUS4ZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02088&json=true","fetch_graph":"https://pith.science/api/pith-number/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/action/storage_attestation","attest_author":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/action/author_attestation","sign_citation":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/action/citation_signature","submit_replication":"https://pith.science/pith/RKEUS4ZUGZB7OMJ7RJJRJFRXZ6/action/replication_record"}},"created_at":"2026-07-05T11:14:32.229833+00:00","updated_at":"2026-07-05T11:14:32.229833+00:00"}