{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QDKOM2IE4VB5YEPKI44KDEEOBX","short_pith_number":"pith:QDKOM2IE","schema_version":"1.0","canonical_sha256":"80d4e66904e543dc11ea4738a1908e0dc3935fb6357ccb3803ed3b43e3abb09e","source":{"kind":"arxiv","id":"2606.21215","version":1},"attestation_state":"computed","paper":{"title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hsin-Yen Sung, Huang-Cheng Chou, Hung-yi Lee, Kuan-Yu Chen, Shrikanth Narayanan, Tzu-Chieh Wei, Yi-Cheng Lin","submitted_at":"2026-06-19T08:32:07Z","abstract_excerpt":"As expressive text-to-speech (TTS) and voice conversion (VC) systems increasingly generate non-verbal vocalizations (NVVs) to enhance naturalness, reliable speaker verification (SV) becomes essential to objectively assess identity consistency across both verbal and non-verbal segments. Yet current SV systems generalize poorly to NVVs, and fine-tuning on NVV data causes catastrophic forgetting of speech performance. We present the first systematic study across 10 NVV types and propose a framework combining frozen Data2Vec self-supervised features with ECAPA-TDNN, enhanced by a Mixture of Expert"},"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":"2606.21215","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-19T08:32:07Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ae66b0699dc52ce5b1749527f81cb65427663a907f7fc6bd073df3e577a26a3c","abstract_canon_sha256":"04afa5ca658eb28531aef7f4de1896df53f5994671e9bd2c4cd009a20850e68e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:33.626196Z","signature_b64":"S0kNGgY+DlhMIhhrpDSgGO3vgWX3fgBAtK0FWeu+ADi4pkIG0VyKwZL0OufxY56vQReEuLoS3P38mY5Ze3bJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80d4e66904e543dc11ea4738a1908e0dc3935fb6357ccb3803ed3b43e3abb09e","last_reissued_at":"2026-06-23T01:12:33.625684Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:33.625684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hsin-Yen Sung, Huang-Cheng Chou, Hung-yi Lee, Kuan-Yu Chen, Shrikanth Narayanan, Tzu-Chieh Wei, Yi-Cheng Lin","submitted_at":"2026-06-19T08:32:07Z","abstract_excerpt":"As expressive text-to-speech (TTS) and voice conversion (VC) systems increasingly generate non-verbal vocalizations (NVVs) to enhance naturalness, reliable speaker verification (SV) becomes essential to objectively assess identity consistency across both verbal and non-verbal segments. Yet current SV systems generalize poorly to NVVs, and fine-tuning on NVV data causes catastrophic forgetting of speech performance. We present the first systematic study across 10 NVV types and propose a framework combining frozen Data2Vec self-supervised features with ECAPA-TDNN, enhanced by a Mixture of Expert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21215","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/2606.21215/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":"2606.21215","created_at":"2026-06-23T01:12:33.625761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21215v1","created_at":"2026-06-23T01:12:33.625761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21215","created_at":"2026-06-23T01:12:33.625761+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDKOM2IE4VB5","created_at":"2026-06-23T01:12:33.625761+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDKOM2IE4VB5YEPK","created_at":"2026-06-23T01:12:33.625761+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDKOM2IE","created_at":"2026-06-23T01:12:33.625761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.21215","citing_title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX","json":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX.json","graph_json":"https://pith.science/api/pith-number/QDKOM2IE4VB5YEPKI44KDEEOBX/graph.json","events_json":"https://pith.science/api/pith-number/QDKOM2IE4VB5YEPKI44KDEEOBX/events.json","paper":"https://pith.science/paper/QDKOM2IE"},"agent_actions":{"view_html":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX","download_json":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX.json","view_paper":"https://pith.science/paper/QDKOM2IE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21215&json=true","fetch_graph":"https://pith.science/api/pith-number/QDKOM2IE4VB5YEPKI44KDEEOBX/graph.json","fetch_events":"https://pith.science/api/pith-number/QDKOM2IE4VB5YEPKI44KDEEOBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/action/storage_attestation","attest_author":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/action/author_attestation","sign_citation":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/action/citation_signature","submit_replication":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/action/replication_record"}},"created_at":"2026-06-23T01:12:33.625761+00:00","updated_at":"2026-06-23T01:12:33.625761+00:00"}