{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DMQLOJO4V3ZUZKXEX6OSWZ46V7","short_pith_number":"pith:DMQLOJO4","schema_version":"1.0","canonical_sha256":"1b20b725dcaef34caae4bf9d2b679eafe90f00b30a0c5128c648156d78b2e536","source":{"kind":"arxiv","id":"2506.14226","version":1},"attestation_state":"computed","paper":{"title":"Investigation of Zero-shot Text-to-Speech Models for Enhancing Short-Utterance Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chao Zhang, Guangzhi Sun, Mingxing Xu, Shuai Wang, Thomas Fang Zheng, Yiyang Zhao, Zehua Chen","submitted_at":"2025-06-17T06:29:58Z","abstract_excerpt":"Short-utterance speaker verification presents significant challenges due to the limited information in brief speech segments, which can undermine accuracy and reliability. Recently, zero-shot text-to-speech (ZS-TTS) systems have made considerable progress in preserving speaker identity. In this study, we explore, for the first time, the use of ZS-TTS systems for test-time data augmentation for speaker verification. We evaluate three state-of-the-art pre-trained ZS-TTS systems, NatureSpeech 3, CosyVoice, and MaskGCT, on the VoxCeleb 1 dataset. Our experimental results show that combining real a"},"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":"2506.14226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-06-17T06:29:58Z","cross_cats_sorted":[],"title_canon_sha256":"9b17dcc06705ee992a753ccd2fc1f7815ed359704eb8a70fa6191d882be1e963","abstract_canon_sha256":"8cedde0d4a82bff31f6ea16a74e3e8c6f5b2edfe57e9542503005edd47e5570a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:51.392628Z","signature_b64":"7M6ZmSf+w7ruVn0P6Kg8JgeYKqeLKIbd0jUkXDcGYvLkkgE3bz033kNtlUnp3bs+SgWKmT4WrmfEN8sPZwxRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b20b725dcaef34caae4bf9d2b679eafe90f00b30a0c5128c648156d78b2e536","last_reissued_at":"2026-07-05T11:22:51.392044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:51.392044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigation of Zero-shot Text-to-Speech Models for Enhancing Short-Utterance Speaker Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chao Zhang, Guangzhi Sun, Mingxing Xu, Shuai Wang, Thomas Fang Zheng, Yiyang Zhao, Zehua Chen","submitted_at":"2025-06-17T06:29:58Z","abstract_excerpt":"Short-utterance speaker verification presents significant challenges due to the limited information in brief speech segments, which can undermine accuracy and reliability. Recently, zero-shot text-to-speech (ZS-TTS) systems have made considerable progress in preserving speaker identity. In this study, we explore, for the first time, the use of ZS-TTS systems for test-time data augmentation for speaker verification. We evaluate three state-of-the-art pre-trained ZS-TTS systems, NatureSpeech 3, CosyVoice, and MaskGCT, on the VoxCeleb 1 dataset. Our experimental results show that combining real a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14226","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/2506.14226/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":"2506.14226","created_at":"2026-07-05T11:22:51.392118+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14226v1","created_at":"2026-07-05T11:22:51.392118+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14226","created_at":"2026-07-05T11:22:51.392118+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMQLOJO4V3ZU","created_at":"2026-07-05T11:22:51.392118+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMQLOJO4V3ZUZKXE","created_at":"2026-07-05T11:22:51.392118+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMQLOJO4","created_at":"2026-07-05T11:22:51.392118+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.14226","citing_title":"Investigation of Zero-shot Text-to-Speech Models for Enhancing Short-Utterance Speaker Verification","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7","json":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7.json","graph_json":"https://pith.science/api/pith-number/DMQLOJO4V3ZUZKXEX6OSWZ46V7/graph.json","events_json":"https://pith.science/api/pith-number/DMQLOJO4V3ZUZKXEX6OSWZ46V7/events.json","paper":"https://pith.science/paper/DMQLOJO4"},"agent_actions":{"view_html":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7","download_json":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7.json","view_paper":"https://pith.science/paper/DMQLOJO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14226&json=true","fetch_graph":"https://pith.science/api/pith-number/DMQLOJO4V3ZUZKXEX6OSWZ46V7/graph.json","fetch_events":"https://pith.science/api/pith-number/DMQLOJO4V3ZUZKXEX6OSWZ46V7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7/action/storage_attestation","attest_author":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7/action/author_attestation","sign_citation":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7/action/citation_signature","submit_replication":"https://pith.science/pith/DMQLOJO4V3ZUZKXEX6OSWZ46V7/action/replication_record"}},"created_at":"2026-07-05T11:22:51.392118+00:00","updated_at":"2026-07-05T11:22:51.392118+00:00"}