{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BPVFPVVOEBTYBRJ536CAEBUZQZ","short_pith_number":"pith:BPVFPVVO","schema_version":"1.0","canonical_sha256":"0bea57d6ae206780c53ddf840206998641c820e79e6c502295b025993c36406e","source":{"kind":"arxiv","id":"2008.06682","version":1},"attestation_state":"computed","paper":{"title":"Jointly Fine-Tuning \"BERT-like\" Self Supervised Models to Improve Multimodal Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Reis, Rivindu Weerasekera, Shamane Siriwardhana, Suranga Nanayakkara","submitted_at":"2020-08-15T08:54:48Z","abstract_excerpt":"Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the use of modality-specific \"BERT-like\" pretrained Self Supervised Learning (SSL) architectures to represent both speech and text modalities for the task of multimodal speech emotion recognition. By conducting experiments on three publicly available datasets (IEMOCAP, CMU-MOSEI, and CMU-MOSI), we show that jointly fine-tuning \"BERT-like\" SSL architectures achiev"},"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":"2008.06682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-15T08:54:48Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"6567d49a0d598bc5c9d4d04b9bfd47f25fc11df7985ce3599b16319732dd4cf3","abstract_canon_sha256":"c6fd295538c647eef4f208df40fea4bb841b11407f8160b2f5c139441091b072"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:04.809504Z","signature_b64":"byAxvabE8DNaD0zlrNH9Jsr0U4fWslH9dUZcCMWlzO5x6jO4L/iHMiElc8jiR91VPTsd9hcgbLJsNBVxqBw+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bea57d6ae206780c53ddf840206998641c820e79e6c502295b025993c36406e","last_reissued_at":"2026-07-05T09:16:04.809043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:04.809043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jointly Fine-Tuning \"BERT-like\" Self Supervised Models to Improve Multimodal Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrew Reis, Rivindu Weerasekera, Shamane Siriwardhana, Suranga Nanayakkara","submitted_at":"2020-08-15T08:54:48Z","abstract_excerpt":"Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the use of modality-specific \"BERT-like\" pretrained Self Supervised Learning (SSL) architectures to represent both speech and text modalities for the task of multimodal speech emotion recognition. By conducting experiments on three publicly available datasets (IEMOCAP, CMU-MOSEI, and CMU-MOSI), we show that jointly fine-tuning \"BERT-like\" SSL architectures achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06682","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/2008.06682/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":"2008.06682","created_at":"2026-07-05T09:16:04.809095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06682v1","created_at":"2026-07-05T09:16:04.809095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06682","created_at":"2026-07-05T09:16:04.809095+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPVFPVVOEBTY","created_at":"2026-07-05T09:16:04.809095+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPVFPVVOEBTYBRJ5","created_at":"2026-07-05T09:16:04.809095+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPVFPVVO","created_at":"2026-07-05T09:16:04.809095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10972","citing_title":"Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ","json":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ.json","graph_json":"https://pith.science/api/pith-number/BPVFPVVOEBTYBRJ536CAEBUZQZ/graph.json","events_json":"https://pith.science/api/pith-number/BPVFPVVOEBTYBRJ536CAEBUZQZ/events.json","paper":"https://pith.science/paper/BPVFPVVO"},"agent_actions":{"view_html":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ","download_json":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ.json","view_paper":"https://pith.science/paper/BPVFPVVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06682&json=true","fetch_graph":"https://pith.science/api/pith-number/BPVFPVVOEBTYBRJ536CAEBUZQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BPVFPVVOEBTYBRJ536CAEBUZQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ/action/storage_attestation","attest_author":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ/action/author_attestation","sign_citation":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ/action/citation_signature","submit_replication":"https://pith.science/pith/BPVFPVVOEBTYBRJ536CAEBUZQZ/action/replication_record"}},"created_at":"2026-07-05T09:16:04.809095+00:00","updated_at":"2026-07-05T09:16:04.809095+00:00"}