{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:73UR7MRLF4K2OLWUDRQED52HTI","short_pith_number":"pith:73UR7MRL","schema_version":"1.0","canonical_sha256":"fee91fb22b2f15a72ed41c6041f7479a3dac18b6c1f2b229a9663605e90dc8ed","source":{"kind":"arxiv","id":"2406.06646","version":1},"attestation_state":"computed","paper":{"title":"Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Rui Liu, Zening Ma","submitted_at":"2024-06-10T02:08:25Z","abstract_excerpt":"Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby neglecting the potential enhancement of emotion task comprehension through emotion prior knowledge in speech. In this paper, we propose an emotion-aware speech representation learning with intensity knowledge. Specifically, we extract frame-level emotion intensities using an established speech-emotion understanding model. Subsequently, we propose a novel emotional "},"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":"2406.06646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-10T02:08:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"dc9feaddf31440a51c7ef6486683e6b8f39250470995620667ec4035ccc0ee97","abstract_canon_sha256":"f41ae44ad892c005d25182ed2c2fc55c41dd24d1a114ff0a8dc304520f6737eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:48.455560Z","signature_b64":"xQ4lUaT/2b5YcdjUDUNmElDHlvEKy1OKtn4saoCc2Khaz2fD4g7uI/b/FKeFIz8zN6lUgNHktFVoV7szkMYADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fee91fb22b2f15a72ed41c6041f7479a3dac18b6c1f2b229a9663605e90dc8ed","last_reissued_at":"2026-07-05T08:29:48.455142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:48.455142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emotion-Aware Speech Self-Supervised Representation Learning with Intensity Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Rui Liu, Zening Ma","submitted_at":"2024-06-10T02:08:25Z","abstract_excerpt":"Speech Self-Supervised Learning (SSL) has demonstrated considerable efficacy in various downstream tasks. Nevertheless, prevailing self-supervised models often overlook the incorporation of emotion-related prior information, thereby neglecting the potential enhancement of emotion task comprehension through emotion prior knowledge in speech. In this paper, we propose an emotion-aware speech representation learning with intensity knowledge. Specifically, we extract frame-level emotion intensities using an established speech-emotion understanding model. Subsequently, we propose a novel emotional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06646","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/2406.06646/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":"2406.06646","created_at":"2026-07-05T08:29:48.455202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06646v1","created_at":"2026-07-05T08:29:48.455202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06646","created_at":"2026-07-05T08:29:48.455202+00:00"},{"alias_kind":"pith_short_12","alias_value":"73UR7MRLF4K2","created_at":"2026-07-05T08:29:48.455202+00:00"},{"alias_kind":"pith_short_16","alias_value":"73UR7MRLF4K2OLWU","created_at":"2026-07-05T08:29:48.455202+00:00"},{"alias_kind":"pith_short_8","alias_value":"73UR7MRL","created_at":"2026-07-05T08:29:48.455202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.18748","citing_title":"Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI","json":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI.json","graph_json":"https://pith.science/api/pith-number/73UR7MRLF4K2OLWUDRQED52HTI/graph.json","events_json":"https://pith.science/api/pith-number/73UR7MRLF4K2OLWUDRQED52HTI/events.json","paper":"https://pith.science/paper/73UR7MRL"},"agent_actions":{"view_html":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI","download_json":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI.json","view_paper":"https://pith.science/paper/73UR7MRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06646&json=true","fetch_graph":"https://pith.science/api/pith-number/73UR7MRLF4K2OLWUDRQED52HTI/graph.json","fetch_events":"https://pith.science/api/pith-number/73UR7MRLF4K2OLWUDRQED52HTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI/action/storage_attestation","attest_author":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI/action/author_attestation","sign_citation":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI/action/citation_signature","submit_replication":"https://pith.science/pith/73UR7MRLF4K2OLWUDRQED52HTI/action/replication_record"}},"created_at":"2026-07-05T08:29:48.455202+00:00","updated_at":"2026-07-05T08:29:48.455202+00:00"}