{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MCVQJPPX247ORJWJU44AYBJ5YY","short_pith_number":"pith:MCVQJPPX","schema_version":"1.0","canonical_sha256":"60ab04bdf7d73ee8a6c9a7380c053dc60e866977fb7fe68dc555ce3b999526bc","source":{"kind":"arxiv","id":"2406.05763","version":3},"attestation_state":"computed","paper":{"title":"WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Binbin Zhang, Dake Guo, Huan Zhao, Kun Song, Lei Xie, Linhan Ma, Liumeng Xue, Shuai Wang, Weiming Xu, Yuepeng Jiang","submitted_at":"2024-06-09T12:32:42Z","abstract_excerpt":"With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we present WenetSpeech4TTS, a multi-domain Mandarin corpus derived from the open-sourced WenetSpeech dataset. Tailored for the text-to-speech tasks, we refined WenetSpeech by adjusting segment boundaries, enhancing the audio quality, and eliminating speaker mixing within each segment. Following a more accurate transcription process and quality-based data filtering process, the obtained WenetSpeech4TTS corpus contains $12,"},"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":"2406.05763","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T12:32:42Z","cross_cats_sorted":[],"title_canon_sha256":"c9c70dcf562910f64dbec79afed4ecfa44d7ed834a3d410b4020204208a3714c","abstract_canon_sha256":"6e3d881b9cc3368cecf7023763d41bd5f1143f895f2c3551f0c0f396eafe6d56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:20.566856Z","signature_b64":"iJalWfAhcLtmHj41/yF8pQOWTpV8GnASs1szuTnGZt6gTAMvpr/rlEoJ6A26FQr7pAnwW0ekl1qjtnnsOl1IDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60ab04bdf7d73ee8a6c9a7380c053dc60e866977fb7fe68dc555ce3b999526bc","last_reissued_at":"2026-07-05T08:34:20.566302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:20.566302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WenetSpeech4TTS: A 12,800-hour Mandarin TTS Corpus for Large Speech Generation Model Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Binbin Zhang, Dake Guo, Huan Zhao, Kun Song, Lei Xie, Linhan Ma, Liumeng Xue, Shuai Wang, Weiming Xu, Yuepeng Jiang","submitted_at":"2024-06-09T12:32:42Z","abstract_excerpt":"With the development of large text-to-speech (TTS) models and scale-up of the training data, state-of-the-art TTS systems have achieved impressive performance. In this paper, we present WenetSpeech4TTS, a multi-domain Mandarin corpus derived from the open-sourced WenetSpeech dataset. Tailored for the text-to-speech tasks, we refined WenetSpeech by adjusting segment boundaries, enhancing the audio quality, and eliminating speaker mixing within each segment. Following a more accurate transcription process and quality-based data filtering process, the obtained WenetSpeech4TTS corpus contains $12,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05763","kind":"arxiv","version":3},"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/2406.05763/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":"2406.05763","created_at":"2026-07-05T08:34:20.566377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.05763v3","created_at":"2026-07-05T08:34:20.566377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05763","created_at":"2026-07-05T08:34:20.566377+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCVQJPPX247O","created_at":"2026-07-05T08:34:20.566377+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCVQJPPX247ORJWJ","created_at":"2026-07-05T08:34:20.566377+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCVQJPPX","created_at":"2026-07-05T08:34:20.566377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23190","citing_title":"FlowTTS-GRPO: Online Reinforcement Learning with Multi-Objective Reward Optimization for Flow-Matching Based Text-to-Speech","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09141","citing_title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":116,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY","json":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY.json","graph_json":"https://pith.science/api/pith-number/MCVQJPPX247ORJWJU44AYBJ5YY/graph.json","events_json":"https://pith.science/api/pith-number/MCVQJPPX247ORJWJU44AYBJ5YY/events.json","paper":"https://pith.science/paper/MCVQJPPX"},"agent_actions":{"view_html":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY","download_json":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY.json","view_paper":"https://pith.science/paper/MCVQJPPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.05763&json=true","fetch_graph":"https://pith.science/api/pith-number/MCVQJPPX247ORJWJU44AYBJ5YY/graph.json","fetch_events":"https://pith.science/api/pith-number/MCVQJPPX247ORJWJU44AYBJ5YY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY/action/storage_attestation","attest_author":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY/action/author_attestation","sign_citation":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY/action/citation_signature","submit_replication":"https://pith.science/pith/MCVQJPPX247ORJWJU44AYBJ5YY/action/replication_record"}},"created_at":"2026-07-05T08:34:20.566377+00:00","updated_at":"2026-07-05T08:34:20.566377+00:00"}