{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DZDTJU6IPQVX4AJYH36BFH65OL","short_pith_number":"pith:DZDTJU6I","schema_version":"1.0","canonical_sha256":"1e4734d3c87c2b7e01383efc129fdd72eb552d5c8244dca7dc709289a09b3b4b","source":{"kind":"arxiv","id":"2306.07848","version":10},"attestation_state":"computed","paper":{"title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Heng Lu, Jianjun Zhao, Jixun Yao, Lei Ma, Wen Fei, Yanni Hu, Yuguang Yang, Yu Pan","submitted_at":"2023-06-13T15:28:10Z","abstract_excerpt":"Contrastive cross-modality pretraining has recently exhibited impressive success in diverse fields, whereas there is limited research on their merits in speech emotion recognition (SER). In this paper, we propose GEmo-CLAP, a kind of gender-attribute-enhanced contrastive language-audio pretraining (CLAP) method for SER. Specifically, we first construct an effective emotion CLAP (Emo-CLAP) for SER, using pre-trained text and audio encoders. Second, given the significance of gender information in SER, two novel multi-task learning based GEmo-CLAP (ML-GEmo-CLAP) and soft label based GEmo-CLAP (SL"},"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":"2306.07848","kind":"arxiv","version":10},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-13T15:28:10Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"2b1833c239b6346ab613c48cf099d42718095cf7b0f7754e3b492c8c1a0d8ce3","abstract_canon_sha256":"fc74fb62f2e606352b1c60056f22633473cd194f83b92a9dd4959625313648f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:46.086797Z","signature_b64":"QjhsTyqC+vY5nnle1NSRvBHaOvlD5ZI2buxR6IDrJQUPFIUsEyjyOw9681uXr1EEex24FDgh1IjOWLTUMgWJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e4734d3c87c2b7e01383efc129fdd72eb552d5c8244dca7dc709289a09b3b4b","last_reissued_at":"2026-07-05T07:19:46.086299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:46.086299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Heng Lu, Jianjun Zhao, Jixun Yao, Lei Ma, Wen Fei, Yanni Hu, Yuguang Yang, Yu Pan","submitted_at":"2023-06-13T15:28:10Z","abstract_excerpt":"Contrastive cross-modality pretraining has recently exhibited impressive success in diverse fields, whereas there is limited research on their merits in speech emotion recognition (SER). In this paper, we propose GEmo-CLAP, a kind of gender-attribute-enhanced contrastive language-audio pretraining (CLAP) method for SER. Specifically, we first construct an effective emotion CLAP (Emo-CLAP) for SER, using pre-trained text and audio encoders. Second, given the significance of gender information in SER, two novel multi-task learning based GEmo-CLAP (ML-GEmo-CLAP) and soft label based GEmo-CLAP (SL"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07848","kind":"arxiv","version":10},"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/2306.07848/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":"2306.07848","created_at":"2026-07-05T07:19:46.086361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07848v10","created_at":"2026-07-05T07:19:46.086361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07848","created_at":"2026-07-05T07:19:46.086361+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZDTJU6IPQVX","created_at":"2026-07-05T07:19:46.086361+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZDTJU6IPQVX4AJY","created_at":"2026-07-05T07:19:46.086361+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZDTJU6I","created_at":"2026-07-05T07:19:46.086361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04048","citing_title":"CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL","json":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL.json","graph_json":"https://pith.science/api/pith-number/DZDTJU6IPQVX4AJYH36BFH65OL/graph.json","events_json":"https://pith.science/api/pith-number/DZDTJU6IPQVX4AJYH36BFH65OL/events.json","paper":"https://pith.science/paper/DZDTJU6I"},"agent_actions":{"view_html":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL","download_json":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL.json","view_paper":"https://pith.science/paper/DZDTJU6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07848&json=true","fetch_graph":"https://pith.science/api/pith-number/DZDTJU6IPQVX4AJYH36BFH65OL/graph.json","fetch_events":"https://pith.science/api/pith-number/DZDTJU6IPQVX4AJYH36BFH65OL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL/action/storage_attestation","attest_author":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL/action/author_attestation","sign_citation":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL/action/citation_signature","submit_replication":"https://pith.science/pith/DZDTJU6IPQVX4AJYH36BFH65OL/action/replication_record"}},"created_at":"2026-07-05T07:19:46.086361+00:00","updated_at":"2026-07-05T07:19:46.086361+00:00"}