{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2B4BUJKSRJKS3YUAEOJV22MM5T","short_pith_number":"pith:2B4BUJKS","schema_version":"1.0","canonical_sha256":"d0781a25528a552de28023935d698cecde492cc6968c595324118979abc90261","source":{"kind":"arxiv","id":"2407.14800","version":1},"attestation_state":"computed","paper":{"title":"Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Cheng Lu, Shiyan Wang, Tianhua Qi, Wenming Zheng, Yan Zhao, Yuan Zong","submitted_at":"2024-07-20T08:13:58Z","abstract_excerpt":"Realistic emotional voice conversion (EVC) aims to enhance emotional diversity of converted audios, making the synthesized voices more authentic and natural. To this end, we propose Emotional Intensity-aware Network (EINet), dynamically adjusting intonation and rhythm by incorporating controllable emotional intensity. To better capture nuances in emotional intensity, we go beyond mere distance measurements among acoustic features. Instead, an emotion evaluator is utilized to precisely quantify speaker's emotional state. By employing an intensity mapper, intensity pseudo-labels are obtained to "},"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":"2407.14800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-20T08:13:58Z","cross_cats_sorted":["cs.SD","eess.SP"],"title_canon_sha256":"983c81ac7b42f2d05dab835d719e27bb3fbae274806ebd6e9f1c4ac89da3459b","abstract_canon_sha256":"7bee293b43783087392a506cd1953bedb1e47f4c5d2d759cd1f3777c98a5241e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:33.908444Z","signature_b64":"tpm7DOS2n75gv4uxzxKxnQXkLAV6civBRDvsY57tLaQXJo+FgYCD0tC5eiR4UPftgDIqRNNhZXl4oV1emXEvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0781a25528a552de28023935d698cecde492cc6968c595324118979abc90261","last_reissued_at":"2026-07-05T08:46:33.908033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:33.908033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Cheng Lu, Shiyan Wang, Tianhua Qi, Wenming Zheng, Yan Zhao, Yuan Zong","submitted_at":"2024-07-20T08:13:58Z","abstract_excerpt":"Realistic emotional voice conversion (EVC) aims to enhance emotional diversity of converted audios, making the synthesized voices more authentic and natural. To this end, we propose Emotional Intensity-aware Network (EINet), dynamically adjusting intonation and rhythm by incorporating controllable emotional intensity. To better capture nuances in emotional intensity, we go beyond mere distance measurements among acoustic features. Instead, an emotion evaluator is utilized to precisely quantify speaker's emotional state. By employing an intensity mapper, intensity pseudo-labels are obtained to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14800","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/2407.14800/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":"2407.14800","created_at":"2026-07-05T08:46:33.908093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14800v1","created_at":"2026-07-05T08:46:33.908093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14800","created_at":"2026-07-05T08:46:33.908093+00:00"},{"alias_kind":"pith_short_12","alias_value":"2B4BUJKSRJKS","created_at":"2026-07-05T08:46:33.908093+00:00"},{"alias_kind":"pith_short_16","alias_value":"2B4BUJKSRJKS3YUA","created_at":"2026-07-05T08:46:33.908093+00:00"},{"alias_kind":"pith_short_8","alias_value":"2B4BUJKS","created_at":"2026-07-05T08:46:33.908093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07116","citing_title":"A Review of Human Emotion Synthesis Based on Generative Technology","ref_index":170,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T","json":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T.json","graph_json":"https://pith.science/api/pith-number/2B4BUJKSRJKS3YUAEOJV22MM5T/graph.json","events_json":"https://pith.science/api/pith-number/2B4BUJKSRJKS3YUAEOJV22MM5T/events.json","paper":"https://pith.science/paper/2B4BUJKS"},"agent_actions":{"view_html":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T","download_json":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T.json","view_paper":"https://pith.science/paper/2B4BUJKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14800&json=true","fetch_graph":"https://pith.science/api/pith-number/2B4BUJKSRJKS3YUAEOJV22MM5T/graph.json","fetch_events":"https://pith.science/api/pith-number/2B4BUJKSRJKS3YUAEOJV22MM5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T/action/storage_attestation","attest_author":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T/action/author_attestation","sign_citation":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T/action/citation_signature","submit_replication":"https://pith.science/pith/2B4BUJKSRJKS3YUAEOJV22MM5T/action/replication_record"}},"created_at":"2026-07-05T08:46:33.908093+00:00","updated_at":"2026-07-05T08:46:33.908093+00:00"}