{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FE5ESRTB6446Z2WUFW4QCS3DID","short_pith_number":"pith:FE5ESRTB","schema_version":"1.0","canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","source":{"kind":"arxiv","id":"2507.00055","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Pedro Morgado, Varsha Pendyala, William Sethares","submitted_at":"2025-06-26T04:13:47Z","abstract_excerpt":"Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues, developing SER systems using both the modalities is beneficial. However, collecting a vast amount of labeled data for their development is expensive. This paper proposes a knowledge distillation framework called LightweightSER (LiSER) that leverages unlabeled audio-visual data for SER, using large teacher models built on advanced speech and face representation mode"},"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":"2507.00055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T04:13:47Z","cross_cats_sorted":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"title_canon_sha256":"2c7cb5a7a69ef8f811c8b3955731c790edef0524d11dbeaec874225f51306fc2","abstract_canon_sha256":"7c97d4f194528f38db1105f3a0afe0628765c6afe1db2b9920c7788e0d764cc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.906711Z","signature_b64":"jEgJiDwVQ72382O4NPFM/Qn3MFQp8OwK5H1SVobdiBm6U6EXWytNSxlyXgVo/W8la3YrqWbXflFQWGehX8FfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"293a494661f739ecead42db9014b6340db2de4fc8630e05204c5d82d51515f89","last_reissued_at":"2026-07-05T11:29:35.906143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.906143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC","cs.MM","eess.AS","eess.IV","eess.SP"],"primary_cat":"cs.LG","authors_text":"Pedro Morgado, Varsha Pendyala, William Sethares","submitted_at":"2025-06-26T04:13:47Z","abstract_excerpt":"Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues, developing SER systems using both the modalities is beneficial. However, collecting a vast amount of labeled data for their development is expensive. This paper proposes a knowledge distillation framework called LightweightSER (LiSER) that leverages unlabeled audio-visual data for SER, using large teacher models built on advanced speech and face representation mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00055","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/2507.00055/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":"2507.00055","created_at":"2026-07-05T11:29:35.906217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00055v1","created_at":"2026-07-05T11:29:35.906217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00055","created_at":"2026-07-05T11:29:35.906217+00:00"},{"alias_kind":"pith_short_12","alias_value":"FE5ESRTB6446","created_at":"2026-07-05T11:29:35.906217+00:00"},{"alias_kind":"pith_short_16","alias_value":"FE5ESRTB6446Z2WU","created_at":"2026-07-05T11:29:35.906217+00:00"},{"alias_kind":"pith_short_8","alias_value":"FE5ESRTB","created_at":"2026-07-05T11:29:35.906217+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/FE5ESRTB6446Z2WUFW4QCS3DID","json":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID.json","graph_json":"https://pith.science/api/pith-number/FE5ESRTB6446Z2WUFW4QCS3DID/graph.json","events_json":"https://pith.science/api/pith-number/FE5ESRTB6446Z2WUFW4QCS3DID/events.json","paper":"https://pith.science/paper/FE5ESRTB"},"agent_actions":{"view_html":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID","download_json":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID.json","view_paper":"https://pith.science/paper/FE5ESRTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00055&json=true","fetch_graph":"https://pith.science/api/pith-number/FE5ESRTB6446Z2WUFW4QCS3DID/graph.json","fetch_events":"https://pith.science/api/pith-number/FE5ESRTB6446Z2WUFW4QCS3DID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/action/storage_attestation","attest_author":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/action/author_attestation","sign_citation":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/action/citation_signature","submit_replication":"https://pith.science/pith/FE5ESRTB6446Z2WUFW4QCS3DID/action/replication_record"}},"created_at":"2026-07-05T11:29:35.906217+00:00","updated_at":"2026-07-05T11:29:35.906217+00:00"}