{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GW3HRILI5XY65IMTSND7YCCBNL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"25d6a9b1bc84a6fd1b0a56f1a6925219b01eaca8ace7e92b7324a015dc2533e2","cross_cats_sorted":["cs.HC","cs.RO","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T19:34:34Z","title_canon_sha256":"674bb9e02934140a34c8daf21cdfbe13420300ed9fce0c4f281452fc16371e26"},"schema_version":"1.0","source":{"id":"2409.10687","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10687","created_at":"2026-07-05T10:32:30Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10687v3","created_at":"2026-07-05T10:32:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10687","created_at":"2026-07-05T10:32:30Z"},{"alias_kind":"pith_short_12","alias_value":"GW3HRILI5XY6","created_at":"2026-07-05T10:32:30Z"},{"alias_kind":"pith_short_16","alias_value":"GW3HRILI5XY65IMT","created_at":"2026-07-05T10:32:30Z"},{"alias_kind":"pith_short_8","alias_value":"GW3HRILI","created_at":"2026-07-05T10:32:30Z"}],"graph_snapshots":[{"event_id":"sha256:a176ea5c86981111e0a33c22e05dbfc6c13399646c1b7d6f40f17a8a79cbaa75","target":"graph","created_at":"2026-07-05T10:32:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.10687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Andrew Frye, Dan O. Popa, Madan Mohan Rayguru, Ruchik Mishra","cross_cats":["cs.HC","cs.RO","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T19:34:34Z","title":"Personalized Speech Emotion Recognition in Human-Robot Interaction using Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10687","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aed2b520b891c560bdb27c6aae7ba8ce10fbb65410ca4e66fe353eed20421f42","target":"record","created_at":"2026-07-05T10:32:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"25d6a9b1bc84a6fd1b0a56f1a6925219b01eaca8ace7e92b7324a015dc2533e2","cross_cats_sorted":["cs.HC","cs.RO","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T19:34:34Z","title_canon_sha256":"674bb9e02934140a34c8daf21cdfbe13420300ed9fce0c4f281452fc16371e26"},"schema_version":"1.0","source":{"id":"2409.10687","kind":"arxiv","version":3}},"canonical_sha256":"35b678a168edf1eea1939347fc08416ae988af16937dc0affcda7b7f2e830211","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35b678a168edf1eea1939347fc08416ae988af16937dc0affcda7b7f2e830211","first_computed_at":"2026-07-05T10:32:30.516307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:32:30.516307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QhhhqxEHOTEJ/tvrhX2D0OGVPtCtuIO59Ghnz74puA8EOEz3wUtQHkF2OFCBq+quL4Rt66qTAKziM8fOMa5iAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:32:30.517294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10687","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aed2b520b891c560bdb27c6aae7ba8ce10fbb65410ca4e66fe353eed20421f42","sha256:a176ea5c86981111e0a33c22e05dbfc6c13399646c1b7d6f40f17a8a79cbaa75"],"state_sha256":"5b3ea5bea977776035fdb5178fdf56ecfc84fc14c8b624ce5417e9e1d99798ac"}