{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PJ45JLV4TSKZLCYNHGFOBBSWED","short_pith_number":"pith:PJ45JLV4","schema_version":"1.0","canonical_sha256":"7a79d4aebc9c95958b0d398ae0865620d2958bdfcda0f130484d3db485c4a25a","source":{"kind":"arxiv","id":"2605.25504","version":1},"attestation_state":"computed","paper":{"title":"Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bagus Tris Atmaja, Sakriani Sakti, Wangzixi Zhou","submitted_at":"2026-05-25T07:08:58Z","abstract_excerpt":"While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have recently emerged, they often lack high-quality, fine-grained annotations, which restricts a model's ability to precisely control NV generation. To address this limitation, we propose a novel approach for fine-grained non-verbal expression synthesis. We curate and reprocess female NV utterances from the EARS corpus, develop a new annotation scheme using tags to en"},"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":"2605.25504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-25T07:08:58Z","cross_cats_sorted":[],"title_canon_sha256":"0647c767e010cce4d94e2cbd61af73a1652bed3dee48511eeaf18f810fd86bcf","abstract_canon_sha256":"4ddc146640db1a44869a182309008856d9b58fcadd45232876a8e6d98860bd5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:39.739842Z","signature_b64":"PvQqHThMzzpXTwL5MFIpmVW1Zecnx82ZZIDcBLHm4N+5V33QS3qpq1FHOPscBVMHt0nOwnSmPWrkTrTOSu+kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a79d4aebc9c95958b0d398ae0865620d2958bdfcda0f130484d3db485c4a25a","last_reissued_at":"2026-05-26T02:04:39.739052Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:39.739052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Natural Emotional Text-To-Speech System with Fine-Grained Non-Verbal Expression Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Bagus Tris Atmaja, Sakriani Sakti, Wangzixi Zhou","submitted_at":"2026-05-25T07:08:58Z","abstract_excerpt":"While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have recently emerged, they often lack high-quality, fine-grained annotations, which restricts a model's ability to precisely control NV generation. To address this limitation, we propose a novel approach for fine-grained non-verbal expression synthesis. We curate and reprocess female NV utterances from the EARS corpus, develop a new annotation scheme using tags to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25504","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/2605.25504/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":"2605.25504","created_at":"2026-05-26T02:04:39.739182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25504v1","created_at":"2026-05-26T02:04:39.739182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25504","created_at":"2026-05-26T02:04:39.739182+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ45JLV4TSKZ","created_at":"2026-05-26T02:04:39.739182+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ45JLV4TSKZLCYN","created_at":"2026-05-26T02:04:39.739182+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ45JLV4","created_at":"2026-05-26T02:04:39.739182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED","json":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED.json","graph_json":"https://pith.science/api/pith-number/PJ45JLV4TSKZLCYNHGFOBBSWED/graph.json","events_json":"https://pith.science/api/pith-number/PJ45JLV4TSKZLCYNHGFOBBSWED/events.json","paper":"https://pith.science/paper/PJ45JLV4"},"agent_actions":{"view_html":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED","download_json":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED.json","view_paper":"https://pith.science/paper/PJ45JLV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25504&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ45JLV4TSKZLCYNHGFOBBSWED/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ45JLV4TSKZLCYNHGFOBBSWED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED/action/storage_attestation","attest_author":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED/action/author_attestation","sign_citation":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED/action/citation_signature","submit_replication":"https://pith.science/pith/PJ45JLV4TSKZLCYNHGFOBBSWED/action/replication_record"}},"created_at":"2026-05-26T02:04:39.739182+00:00","updated_at":"2026-05-26T02:04:39.739182+00:00"}