{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BKB5ELWTQXSREC6H4NJQGSK56U","short_pith_number":"pith:BKB5ELWT","schema_version":"1.0","canonical_sha256":"0a83d22ed385e5120bc7e35303495df53bf630ee95e2d00ae7677f8087bb6321","source":{"kind":"arxiv","id":"2312.11974","version":2},"attestation_state":"computed","paper":{"title":"Ms-senet: Enhancing Speech Emotion Recognition Through Multi-scale Feature Fusion With Squeeze-and-excitation Blocks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dichucheng Li, Haojun Fei, Mengbo Li, Yaoxuan Wang, Yuanzhong Zheng, Yulun Wu","submitted_at":"2023-12-19T09:11:55Z","abstract_excerpt":"Speech Emotion Recognition (SER) has become a growing focus of research in human-computer interaction. Spatiotemporal features play a crucial role in SER, yet current research lacks comprehensive spatiotemporal feature learning. This paper focuses on addressing this gap by proposing a novel approach. In this paper, we employ Convolutional Neural Network (CNN) with varying kernel sizes for spatial and temporal feature extraction. Additionally, we introduce Squeeze-and-Excitation (SE) modules to capture and fuse multi-scale features, facilitating effective information fusion for improved emotion"},"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":"2312.11974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-12-19T09:11:55Z","cross_cats_sorted":["cs.HC","eess.AS"],"title_canon_sha256":"92fd09f6fbbdb1093be3afa2f872986c8873e5a3ccb3ba30b525134325a35de6","abstract_canon_sha256":"df5db5fe0bf61dc289be14e9ccc2b44f6b42623ee55c19996e48f8ebef34cc38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:12.761070Z","signature_b64":"oJu3uqknZzuf0rx7/qKDlDnZlEk37GLvgIGt4d8Al9MrWVfIfX05d3Bijfame7025Id9jjN3N+76pTF0G7NxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a83d22ed385e5120bc7e35303495df53bf630ee95e2d00ae7677f8087bb6321","last_reissued_at":"2026-07-05T07:28:12.760597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:12.760597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ms-senet: Enhancing Speech Emotion Recognition Through Multi-scale Feature Fusion With Squeeze-and-excitation Blocks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dichucheng Li, Haojun Fei, Mengbo Li, Yaoxuan Wang, Yuanzhong Zheng, Yulun Wu","submitted_at":"2023-12-19T09:11:55Z","abstract_excerpt":"Speech Emotion Recognition (SER) has become a growing focus of research in human-computer interaction. Spatiotemporal features play a crucial role in SER, yet current research lacks comprehensive spatiotemporal feature learning. This paper focuses on addressing this gap by proposing a novel approach. In this paper, we employ Convolutional Neural Network (CNN) with varying kernel sizes for spatial and temporal feature extraction. Additionally, we introduce Squeeze-and-Excitation (SE) modules to capture and fuse multi-scale features, facilitating effective information fusion for improved emotion"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11974","kind":"arxiv","version":2},"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/2312.11974/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":"2312.11974","created_at":"2026-07-05T07:28:12.760655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11974v2","created_at":"2026-07-05T07:28:12.760655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11974","created_at":"2026-07-05T07:28:12.760655+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKB5ELWTQXSR","created_at":"2026-07-05T07:28:12.760655+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKB5ELWTQXSREC6H","created_at":"2026-07-05T07:28:12.760655+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKB5ELWT","created_at":"2026-07-05T07:28:12.760655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U","json":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U.json","graph_json":"https://pith.science/api/pith-number/BKB5ELWTQXSREC6H4NJQGSK56U/graph.json","events_json":"https://pith.science/api/pith-number/BKB5ELWTQXSREC6H4NJQGSK56U/events.json","paper":"https://pith.science/paper/BKB5ELWT"},"agent_actions":{"view_html":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U","download_json":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U.json","view_paper":"https://pith.science/paper/BKB5ELWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11974&json=true","fetch_graph":"https://pith.science/api/pith-number/BKB5ELWTQXSREC6H4NJQGSK56U/graph.json","fetch_events":"https://pith.science/api/pith-number/BKB5ELWTQXSREC6H4NJQGSK56U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U/action/storage_attestation","attest_author":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U/action/author_attestation","sign_citation":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U/action/citation_signature","submit_replication":"https://pith.science/pith/BKB5ELWTQXSREC6H4NJQGSK56U/action/replication_record"}},"created_at":"2026-07-05T07:28:12.760655+00:00","updated_at":"2026-07-05T07:28:12.760655+00:00"}