{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FX7DF4G42Y5ZH7Y63Q53VVINZX","short_pith_number":"pith:FX7DF4G4","schema_version":"1.0","canonical_sha256":"2dfe32f0dcd63b93ff1edc3bbad50dcdcb6803221c18adb0d209e032c97e698a","source":{"kind":"arxiv","id":"2403.02167","version":3},"attestation_state":"computed","paper":{"title":"EMOVOME: A Dataset for Emotion Recognition in Spontaneous Real-Life Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Javier Mar\\'in-Morales, Luc\\'ia G\\'omez-Zaragoz\\'a, Mar\\'ia Jos\\'e Castro-Bleda, Mariano Alca\\~niz Raya, Roc\\'io del Amor, Valery Naranjo","submitted_at":"2024-03-04T16:13:39Z","abstract_excerpt":"Spontaneous datasets for Speech Emotion Recognition (SER) are scarce and frequently derived from laboratory environments or staged scenarios, such as TV shows, limiting their application in real-world contexts. We developed and publicly released the Emotional Voice Messages (EMOVOME) dataset, including 999 voice messages from real conversations of 100 Spanish speakers on a messaging app, labeled in continuous and discrete emotions by expert and non-expert annotators. We evaluated speaker-independent SER models using acoustic features as baseline and transformer-based models. We compared the re"},"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":"2403.02167","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-04T16:13:39Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"113b31bf39f6212161aed5ce874a16b86d51e5cb92fdf3081dbcaf4c9217362a","abstract_canon_sha256":"adf0314e75cae66dc7f6a8174176d0b6742853e87c334e340891a05eb821f226"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:07.870649Z","signature_b64":"VKEl9hxDP4pOmOI8suJ2bSlr1T9litKSd/8jrxNDxBcWJ303MqKosJHzMVS0+G8FdoeS+ihiv2CovyMxWS3jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dfe32f0dcd63b93ff1edc3bbad50dcdcb6803221c18adb0d209e032c97e698a","last_reissued_at":"2026-07-05T09:44:07.870162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:07.870162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMOVOME: A Dataset for Emotion Recognition in Spontaneous Real-Life Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Javier Mar\\'in-Morales, Luc\\'ia G\\'omez-Zaragoz\\'a, Mar\\'ia Jos\\'e Castro-Bleda, Mariano Alca\\~niz Raya, Roc\\'io del Amor, Valery Naranjo","submitted_at":"2024-03-04T16:13:39Z","abstract_excerpt":"Spontaneous datasets for Speech Emotion Recognition (SER) are scarce and frequently derived from laboratory environments or staged scenarios, such as TV shows, limiting their application in real-world contexts. We developed and publicly released the Emotional Voice Messages (EMOVOME) dataset, including 999 voice messages from real conversations of 100 Spanish speakers on a messaging app, labeled in continuous and discrete emotions by expert and non-expert annotators. We evaluated speaker-independent SER models using acoustic features as baseline and transformer-based models. We compared the re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02167","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/2403.02167/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":"2403.02167","created_at":"2026-07-05T09:44:07.870219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02167v3","created_at":"2026-07-05T09:44:07.870219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02167","created_at":"2026-07-05T09:44:07.870219+00:00"},{"alias_kind":"pith_short_12","alias_value":"FX7DF4G42Y5Z","created_at":"2026-07-05T09:44:07.870219+00:00"},{"alias_kind":"pith_short_16","alias_value":"FX7DF4G42Y5ZH7Y6","created_at":"2026-07-05T09:44:07.870219+00:00"},{"alias_kind":"pith_short_8","alias_value":"FX7DF4G4","created_at":"2026-07-05T09:44:07.870219+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12580","citing_title":"\"How to Explore Biases in Speech Emotion AI with Users?\" A Speech-Emotion-Acting Study Exploring Age and Language Biases","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX","json":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX.json","graph_json":"https://pith.science/api/pith-number/FX7DF4G42Y5ZH7Y63Q53VVINZX/graph.json","events_json":"https://pith.science/api/pith-number/FX7DF4G42Y5ZH7Y63Q53VVINZX/events.json","paper":"https://pith.science/paper/FX7DF4G4"},"agent_actions":{"view_html":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX","download_json":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX.json","view_paper":"https://pith.science/paper/FX7DF4G4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02167&json=true","fetch_graph":"https://pith.science/api/pith-number/FX7DF4G42Y5ZH7Y63Q53VVINZX/graph.json","fetch_events":"https://pith.science/api/pith-number/FX7DF4G42Y5ZH7Y63Q53VVINZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX/action/storage_attestation","attest_author":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX/action/author_attestation","sign_citation":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX/action/citation_signature","submit_replication":"https://pith.science/pith/FX7DF4G42Y5ZH7Y63Q53VVINZX/action/replication_record"}},"created_at":"2026-07-05T09:44:07.870219+00:00","updated_at":"2026-07-05T09:44:07.870219+00:00"}