{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YMBMRENXLTDLQMJ7L5DV2R33SV","short_pith_number":"pith:YMBMRENX","schema_version":"1.0","canonical_sha256":"c302c891b75cc6b8313f5f475d477b956efebd9f5fcd2969834926ed5b8a46ab","source":{"kind":"arxiv","id":"2409.08711","version":2},"attestation_state":"computed","paper":{"title":"Text-To-Speech Synthesis In The Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Hye-Jin Shim, Jee-weon Jung, Ji-Hoon Kim, Jinchuan Tian, Joon Son Chung, Nicholas Evans, Seyun Um, Shinji Watanabe, Shinnosuke Takamichi, Soumi Maiti, Wangyou Zhang, Xin Wang, Yihan Wu, Yuta Matsunaga","submitted_at":"2024-09-13T10:58:55Z","abstract_excerpt":"Traditional Text-to-Speech (TTS) systems rely on studio-quality speech recorded in controlled settings.a Recently, an effort known as noisy-TTS training has emerged, aiming to utilize in-the-wild data. However, the lack of dedicated datasets has been a significant limitation. We introduce the TTS In the Wild (TITW) dataset, which is publicly available, created through a fully automated pipeline applied to the VoxCeleb1 dataset. It comprises two training sets: TITW-Hard, derived from the transcription, segmentation, and selection of raw VoxCeleb1 data, and TITW-Easy, which incorporates addition"},"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":"2409.08711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T10:58:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f8dacea445459a2937f0eab64d66c1dd79bf534035b5a5e67ed610f8c700b67","abstract_canon_sha256":"55b0c06309460aed64f39141a51926fae2ab7190205122824e32a7a6d9163a2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:12.530798Z","signature_b64":"mHvDn8K0EhXHe7bV+gZwsw/3dRMbCG/S5fDwRc3SyLurJjARr4RFyABVoPLkvVEIeYd2DlKOkAInHKDRZDN3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c302c891b75cc6b8313f5f475d477b956efebd9f5fcd2969834926ed5b8a46ab","last_reissued_at":"2026-07-05T11:13:12.530235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:12.530235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-To-Speech Synthesis In The Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"eess.AS","authors_text":"Hye-Jin Shim, Jee-weon Jung, Ji-Hoon Kim, Jinchuan Tian, Joon Son Chung, Nicholas Evans, Seyun Um, Shinji Watanabe, Shinnosuke Takamichi, Soumi Maiti, Wangyou Zhang, Xin Wang, Yihan Wu, Yuta Matsunaga","submitted_at":"2024-09-13T10:58:55Z","abstract_excerpt":"Traditional Text-to-Speech (TTS) systems rely on studio-quality speech recorded in controlled settings.a Recently, an effort known as noisy-TTS training has emerged, aiming to utilize in-the-wild data. However, the lack of dedicated datasets has been a significant limitation. We introduce the TTS In the Wild (TITW) dataset, which is publicly available, created through a fully automated pipeline applied to the VoxCeleb1 dataset. It comprises two training sets: TITW-Hard, derived from the transcription, segmentation, and selection of raw VoxCeleb1 data, and TITW-Easy, which incorporates addition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08711","kind":"arxiv","version":2},"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/2409.08711/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":"2409.08711","created_at":"2026-07-05T11:13:12.530300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08711v2","created_at":"2026-07-05T11:13:12.530300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08711","created_at":"2026-07-05T11:13:12.530300+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMBMRENXLTDL","created_at":"2026-07-05T11:13:12.530300+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMBMRENXLTDLQMJ7","created_at":"2026-07-05T11:13:12.530300+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMBMRENX","created_at":"2026-07-05T11:13:12.530300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23859","citing_title":"Natural Yet Challenging to Detect: Robust In-the-Wild TTS through EMA and Dual-Scoring Prompt Selection -- Submission for WildSpoof 2026 TTS Track","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV","json":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV.json","graph_json":"https://pith.science/api/pith-number/YMBMRENXLTDLQMJ7L5DV2R33SV/graph.json","events_json":"https://pith.science/api/pith-number/YMBMRENXLTDLQMJ7L5DV2R33SV/events.json","paper":"https://pith.science/paper/YMBMRENX"},"agent_actions":{"view_html":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV","download_json":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV.json","view_paper":"https://pith.science/paper/YMBMRENX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08711&json=true","fetch_graph":"https://pith.science/api/pith-number/YMBMRENXLTDLQMJ7L5DV2R33SV/graph.json","fetch_events":"https://pith.science/api/pith-number/YMBMRENXLTDLQMJ7L5DV2R33SV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV/action/storage_attestation","attest_author":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV/action/author_attestation","sign_citation":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV/action/citation_signature","submit_replication":"https://pith.science/pith/YMBMRENXLTDLQMJ7L5DV2R33SV/action/replication_record"}},"created_at":"2026-07-05T11:13:12.530300+00:00","updated_at":"2026-07-05T11:13:12.530300+00:00"}