{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QDKOM2IE4VB5YEPKI44KDEEOBX","short_pith_number":"pith:QDKOM2IE","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"},"canonical_sha256":"80d4e66904e543dc11ea4738a1908e0dc3935fb6357ccb3803ed3b43e3abb09e","source":{"kind":"arxiv","id":"2606.21215","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21215","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21215v1","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21215","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"QDKOM2IE4VB5","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"QDKOM2IE4VB5YEPK","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"QDKOM2IE","created_at":"2026-06-23T01:12:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QDKOM2IE4VB5YEPKI44KDEEOBX","target":"record","payload":{"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"},"canonical_sha256":"80d4e66904e543dc11ea4738a1908e0dc3935fb6357ccb3803ed3b43e3abb09e","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"},"source_kind":"arxiv","source_id":"2606.21215","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ve9mRqvryp1BIwvHqm4DRrY5BIS/4S1PDKrm/MusE4NxPfLG2xO5nWlnYiXlTXrssNZZwJ24WjXuzHD/6+dfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:13:51.372421Z"},"content_sha256":"036ecde45701d40fec35ce58c2c8346cb910bff0fc97ae84d1d287eef1767e87","schema_version":"1.0","event_id":"sha256:036ecde45701d40fec35ce58c2c8346cb910bff0fc97ae84d1d287eef1767e87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QDKOM2IE4VB5YEPKI44KDEEOBX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:12:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bIu6WB/HnqHpwWcYjVKrTqCkzzcN7W6LFHFSJBUM3NUNjaGuCiEdofb4qH/UuBtgq3Mt/mZi4TeNZfsNaDRnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T19:13:51.372802Z"},"content_sha256":"f0baa0be250a861b8675fd537995522274b5ddda7ecbd69c97a5794e3e0978bf","schema_version":"1.0","event_id":"sha256:f0baa0be250a861b8675fd537995522274b5ddda7ecbd69c97a5794e3e0978bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/bundle.json","state_url":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T19:13:51Z","links":{"resolver":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX","bundle":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/bundle.json","state":"https://pith.science/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDKOM2IE4VB5YEPKI44KDEEOBX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QDKOM2IE4VB5YEPKI44KDEEOBX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"04afa5ca658eb28531aef7f4de1896df53f5994671e9bd2c4cd009a20850e68e","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-19T08:32:07Z","title_canon_sha256":"ae66b0699dc52ce5b1749527f81cb65427663a907f7fc6bd073df3e577a26a3c"},"schema_version":"1.0","source":{"id":"2606.21215","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21215","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21215v1","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21215","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"pith_short_12","alias_value":"QDKOM2IE4VB5","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"pith_short_16","alias_value":"QDKOM2IE4VB5YEPK","created_at":"2026-06-23T01:12:33Z"},{"alias_kind":"pith_short_8","alias_value":"QDKOM2IE","created_at":"2026-06-23T01:12:33Z"}],"graph_snapshots":[{"event_id":"sha256:f0baa0be250a861b8675fd537995522274b5ddda7ecbd69c97a5794e3e0978bf","target":"graph","created_at":"2026-06-23T01:12:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.21215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hsin-Yen Sung, Huang-Cheng Chou, Hung-yi Lee, Kuan-Yu Chen, Shrikanth Narayanan, Tzu-Chieh Wei, Yi-Cheng Lin","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-19T08:32:07Z","title":"Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21215","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:036ecde45701d40fec35ce58c2c8346cb910bff0fc97ae84d1d287eef1767e87","target":"record","created_at":"2026-06-23T01:12:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"04afa5ca658eb28531aef7f4de1896df53f5994671e9bd2c4cd009a20850e68e","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-19T08:32:07Z","title_canon_sha256":"ae66b0699dc52ce5b1749527f81cb65427663a907f7fc6bd073df3e577a26a3c"},"schema_version":"1.0","source":{"id":"2606.21215","kind":"arxiv","version":1}},"canonical_sha256":"80d4e66904e543dc11ea4738a1908e0dc3935fb6357ccb3803ed3b43e3abb09e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80d4e66904e543dc11ea4738a1908e0dc3935fb6357ccb3803ed3b43e3abb09e","first_computed_at":"2026-06-23T01:12:33.625684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:33.625684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S0kNGgY+DlhMIhhrpDSgGO3vgWX3fgBAtK0FWeu+ADi4pkIG0VyKwZL0OufxY56vQReEuLoS3P38mY5Ze3bJAA==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:33.626196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21215","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:036ecde45701d40fec35ce58c2c8346cb910bff0fc97ae84d1d287eef1767e87","sha256:f0baa0be250a861b8675fd537995522274b5ddda7ecbd69c97a5794e3e0978bf"],"state_sha256":"1de71cf749c544ea723a08718a306050c193e6bb8971baded8da2ce922090412"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PB414spdaHqt//57QXmcvcG+TrmPgA39fOkxDHdDmcHHiUjWg2hr3JT7omTCWFVNHfyZRNmbf1qwQsyDHB2UBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T19:13:51.374890Z","bundle_sha256":"435e12e1697781ad5bd890926e7a32e9ba55e2e10b0bc948a72640eb7e27e4f9"}}