{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EWICAWTPECSCIMXPXFFCJX4ERX","short_pith_number":"pith:EWICAWTP","schema_version":"1.0","canonical_sha256":"2590205a6f20a42432efb94a24df848de8a7396d91ae8dec88fc591d035f7eb1","source":{"kind":"arxiv","id":"2507.04048","version":1},"attestation_state":"computed","paper":{"title":"CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiacheng Shi, Yanfu Zhang, Ye Gao","submitted_at":"2025-07-05T14:16:06Z","abstract_excerpt":"Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP) provides strong multimodal alignment, it lacks dedicated mechanisms for capturing emotional cues, making it suboptimal for SER. To address this, we propose CLEP-DG, a framework that enhances CLAP's robustness in emotion recognition. First, we fine-tune CLAP to obtain CLEP, adapting it on large-scale emotional speech datasets to better encode emotion-relevant featu"},"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":"2507.04048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-07-05T14:16:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"05aa40222cdd26cf0c2e3bd7c1bd4a45cb0b1414d3d9b9725858b85cfdd9838b","abstract_canon_sha256":"be7ec65aee7002533e0722c12af1cf5391d2bc0c2765862fe1a1fdf691c11ca5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:41.360392Z","signature_b64":"4mg5oTECo8qkuDXcKD/4KYWl4com+W+VivU1bbZE24eJ/dxTmf5yAiA8yPmeth2sIYECM/h3vfOu0XUZCiOpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2590205a6f20a42432efb94a24df848de8a7396d91ae8dec88fc591d035f7eb1","last_reissued_at":"2026-07-05T11:32:41.359892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:41.359892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLEP-DG: Contrastive Learning for Speech Emotion Domain Generalization via Soft Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiacheng Shi, Yanfu Zhang, Ye Gao","submitted_at":"2025-07-05T14:16:06Z","abstract_excerpt":"Speech Emotion Recognition (SER) is fundamental to affective computing and human-computer interaction, yet existing models struggle to generalize across diverse acoustic conditions. While Contrastive Language-Audio Pretraining (CLAP) provides strong multimodal alignment, it lacks dedicated mechanisms for capturing emotional cues, making it suboptimal for SER. To address this, we propose CLEP-DG, a framework that enhances CLAP's robustness in emotion recognition. First, we fine-tune CLAP to obtain CLEP, adapting it on large-scale emotional speech datasets to better encode emotion-relevant featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04048","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/2507.04048/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":"2507.04048","created_at":"2026-07-05T11:32:41.359948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04048v1","created_at":"2026-07-05T11:32:41.359948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04048","created_at":"2026-07-05T11:32:41.359948+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWICAWTPECSC","created_at":"2026-07-05T11:32:41.359948+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWICAWTPECSCIMXP","created_at":"2026-07-05T11:32:41.359948+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWICAWTP","created_at":"2026-07-05T11:32:41.359948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX","json":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX.json","graph_json":"https://pith.science/api/pith-number/EWICAWTPECSCIMXPXFFCJX4ERX/graph.json","events_json":"https://pith.science/api/pith-number/EWICAWTPECSCIMXPXFFCJX4ERX/events.json","paper":"https://pith.science/paper/EWICAWTP"},"agent_actions":{"view_html":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX","download_json":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX.json","view_paper":"https://pith.science/paper/EWICAWTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04048&json=true","fetch_graph":"https://pith.science/api/pith-number/EWICAWTPECSCIMXPXFFCJX4ERX/graph.json","fetch_events":"https://pith.science/api/pith-number/EWICAWTPECSCIMXPXFFCJX4ERX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX/action/storage_attestation","attest_author":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX/action/author_attestation","sign_citation":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX/action/citation_signature","submit_replication":"https://pith.science/pith/EWICAWTPECSCIMXPXFFCJX4ERX/action/replication_record"}},"created_at":"2026-07-05T11:32:41.359948+00:00","updated_at":"2026-07-05T11:32:41.359948+00:00"}