{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7HICUO3SULY6PXQGIRJELT2P2L","short_pith_number":"pith:7HICUO3S","schema_version":"1.0","canonical_sha256":"f9d02a3b72a2f1e7de06445245cf4fd2e052c72f1fc8dc522a171d0b829a5e49","source":{"kind":"arxiv","id":"2412.08237","version":2},"attestation_state":"computed","paper":{"title":"TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Changwei Ma, Dinghao Zhou, Di Wu, Fuping Pan, Mengtao Xing, Shengqiang Li, Shun Lei, Xingchen Song, Yuekai Zhang, Zhendong Peng, Zhiyong Wu","submitted_at":"2024-12-11T09:38:50Z","abstract_excerpt":"It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each stage (e.g., speech denoising, speech enhancement, speaker diarization, and punctuation models), which themselves demand high-quality training data and are rarely open-sourced. Even with state-of-the-art models, issues persist, such as incomplete background noise removal and misalignment between punctuation and actual speech pauses. Moreover, the stringent filte"},"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":"2412.08237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T09:38:50Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"768c8a0ebe052818bcc45eef85c2a0f14b11377d99be48614af6db00f41a008d","abstract_canon_sha256":"c379e7aefe37f4df2c58a7b9b3b54f153b8d2710462a698db9cc8e01054f9a65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:18.069250Z","signature_b64":"aJRVFiIcvh2KDIjJZ+WF6gPqNAQIRYPKgoBX+vBuHhSi2yR6clZzzeQpzJD8yaTBS24qmMao3M4izD5B/otSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9d02a3b72a2f1e7de06445245cf4fd2e052c72f1fc8dc522a171d0b829a5e49","last_reissued_at":"2026-07-05T09:48:18.068773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:18.068773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Changwei Ma, Dinghao Zhou, Di Wu, Fuping Pan, Mengtao Xing, Shengqiang Li, Shun Lei, Xingchen Song, Yuekai Zhang, Zhendong Peng, Zhiyong Wu","submitted_at":"2024-12-11T09:38:50Z","abstract_excerpt":"It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each stage (e.g., speech denoising, speech enhancement, speaker diarization, and punctuation models), which themselves demand high-quality training data and are rarely open-sourced. Even with state-of-the-art models, issues persist, such as incomplete background noise removal and misalignment between punctuation and actual speech pauses. Moreover, the stringent filte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08237","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/2412.08237/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":"2412.08237","created_at":"2026-07-05T09:48:18.068829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08237v2","created_at":"2026-07-05T09:48:18.068829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08237","created_at":"2026-07-05T09:48:18.068829+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HICUO3SULY6","created_at":"2026-07-05T09:48:18.068829+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HICUO3SULY6PXQG","created_at":"2026-07-05T09:48:18.068829+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HICUO3S","created_at":"2026-07-05T09:48:18.068829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25369","citing_title":"Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19798","citing_title":"Borderless Long Speech Synthesis","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L","json":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L.json","graph_json":"https://pith.science/api/pith-number/7HICUO3SULY6PXQGIRJELT2P2L/graph.json","events_json":"https://pith.science/api/pith-number/7HICUO3SULY6PXQGIRJELT2P2L/events.json","paper":"https://pith.science/paper/7HICUO3S"},"agent_actions":{"view_html":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L","download_json":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L.json","view_paper":"https://pith.science/paper/7HICUO3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08237&json=true","fetch_graph":"https://pith.science/api/pith-number/7HICUO3SULY6PXQGIRJELT2P2L/graph.json","fetch_events":"https://pith.science/api/pith-number/7HICUO3SULY6PXQGIRJELT2P2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L/action/storage_attestation","attest_author":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L/action/author_attestation","sign_citation":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L/action/citation_signature","submit_replication":"https://pith.science/pith/7HICUO3SULY6PXQGIRJELT2P2L/action/replication_record"}},"created_at":"2026-07-05T09:48:18.068829+00:00","updated_at":"2026-07-05T09:48:18.068829+00:00"}