{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GW3HRILI5XY65IMTSND7YCCBNL","short_pith_number":"pith:GW3HRILI","schema_version":"1.0","canonical_sha256":"35b678a168edf1eea1939347fc08416ae988af16937dc0affcda7b7f2e830211","source":{"kind":"arxiv","id":"2409.10687","version":3},"attestation_state":"computed","paper":{"title":"Personalized Speech Emotion Recognition in Human-Robot Interaction using Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.RO","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Frye, Dan O. Popa, Madan Mohan Rayguru, Ruchik Mishra","submitted_at":"2024-09-16T19:34:34Z","abstract_excerpt":"Emotions are an essential element in verbal communication, so understanding individuals' affect during a human-robot interaction (HRI) becomes imperative. This paper investigates the application of vision transformer models, namely ViT (Vision Transformers) and BEiT (BERT Pre-Training of Image Transformers) pipelines, for Speech Emotion Recognition (SER) in HRI. The focus is to generalize the SER models for individual speech characteristics by fine-tuning these models on benchmark datasets and exploiting ensemble methods. For this purpose, we collected audio data from different human subjects "},"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":"2409.10687","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T19:34:34Z","cross_cats_sorted":["cs.HC","cs.RO","cs.SD"],"title_canon_sha256":"674bb9e02934140a34c8daf21cdfbe13420300ed9fce0c4f281452fc16371e26","abstract_canon_sha256":"25d6a9b1bc84a6fd1b0a56f1a6925219b01eaca8ace7e92b7324a015dc2533e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:30.517294Z","signature_b64":"QhhhqxEHOTEJ/tvrhX2D0OGVPtCtuIO59Ghnz74puA8EOEz3wUtQHkF2OFCBq+quL4Rt66qTAKziM8fOMa5iAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b678a168edf1eea1939347fc08416ae988af16937dc0affcda7b7f2e830211","last_reissued_at":"2026-07-05T10:32:30.516307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:30.516307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Personalized Speech Emotion Recognition in Human-Robot Interaction using Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.RO","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Frye, Dan O. Popa, Madan Mohan Rayguru, Ruchik Mishra","submitted_at":"2024-09-16T19:34:34Z","abstract_excerpt":"Emotions are an essential element in verbal communication, so understanding individuals' affect during a human-robot interaction (HRI) becomes imperative. This paper investigates the application of vision transformer models, namely ViT (Vision Transformers) and BEiT (BERT Pre-Training of Image Transformers) pipelines, for Speech Emotion Recognition (SER) in HRI. The focus is to generalize the SER models for individual speech characteristics by fine-tuning these models on benchmark datasets and exploiting ensemble methods. For this purpose, we collected audio data from different human subjects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10687","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/2409.10687/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":"2409.10687","created_at":"2026-07-05T10:32:30.516461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10687v3","created_at":"2026-07-05T10:32:30.516461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10687","created_at":"2026-07-05T10:32:30.516461+00:00"},{"alias_kind":"pith_short_12","alias_value":"GW3HRILI5XY6","created_at":"2026-07-05T10:32:30.516461+00:00"},{"alias_kind":"pith_short_16","alias_value":"GW3HRILI5XY65IMT","created_at":"2026-07-05T10:32:30.516461+00:00"},{"alias_kind":"pith_short_8","alias_value":"GW3HRILI","created_at":"2026-07-05T10:32:30.516461+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.06919","citing_title":"Shake-VLA: Vision-Language-Action Model-Based System for Bimanual Robotic Manipulations and Liquid Mixing","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL","json":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL.json","graph_json":"https://pith.science/api/pith-number/GW3HRILI5XY65IMTSND7YCCBNL/graph.json","events_json":"https://pith.science/api/pith-number/GW3HRILI5XY65IMTSND7YCCBNL/events.json","paper":"https://pith.science/paper/GW3HRILI"},"agent_actions":{"view_html":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL","download_json":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL.json","view_paper":"https://pith.science/paper/GW3HRILI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10687&json=true","fetch_graph":"https://pith.science/api/pith-number/GW3HRILI5XY65IMTSND7YCCBNL/graph.json","fetch_events":"https://pith.science/api/pith-number/GW3HRILI5XY65IMTSND7YCCBNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL/action/storage_attestation","attest_author":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL/action/author_attestation","sign_citation":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL/action/citation_signature","submit_replication":"https://pith.science/pith/GW3HRILI5XY65IMTSND7YCCBNL/action/replication_record"}},"created_at":"2026-07-05T10:32:30.516461+00:00","updated_at":"2026-07-05T10:32:30.516461+00:00"}