{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X6PJYWIAU3RLQZTN26VSKQ7M5P","short_pith_number":"pith:X6PJYWIA","schema_version":"1.0","canonical_sha256":"bf9e9c5900a6e2b8666dd7ab2543ecebde0c333a6fd8eddcfe16708666db9e9d","source":{"kind":"arxiv","id":"2407.05361","version":3},"attestation_state":"computed","paper":{"title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Chaoren Wang, Chen Yang, Haorui He, Hua Hua, Jiaqi Li, Kai Chen, Liwei Liu, Peiyang Shi, Pengyuan Zhang, Xuyuan Li, Yicheng Gu, Yuancheng Wang, Zengqiang Shang, Zhizheng Wu","submitted_at":"2024-07-07T13:24:54Z","abstract_excerpt":"Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech remains a challenge due to the scarcity of large, diverse, and spontaneous speech datasets. In response, we introduce Emilia, the first large-scale, multilingual, and diverse speech generation dataset. Emilia starts with over 101k hours of speech across six languages, covering a wide range of speaking styles to enable more natural and spontaneous speech generation. To facilitate the scale-up of Emilia, we also present E"},"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":"2407.05361","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-07T13:24:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"333e03d427a3a0857edaa59032419ed887cbc1e7977bc6ee1cfdb239d08a043f","abstract_canon_sha256":"ebbc8fed680b873cfab82d11862a14991bb5325c5ab89426ac110b5616dcdc33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:11.096592Z","signature_b64":"a1qWIDHHLCOwOnBV3EQBrU5vNsyf41wcedYpFshGpBNq8uPioWZaBP8DWqP/EgsAIJlU8EnrlKXEGrZvKcu4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf9e9c5900a6e2b8666dd7ab2543ecebde0c333a6fd8eddcfe16708666db9e9d","last_reissued_at":"2026-07-05T09:04:11.096098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:11.096098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Chaoren Wang, Chen Yang, Haorui He, Hua Hua, Jiaqi Li, Kai Chen, Liwei Liu, Peiyang Shi, Pengyuan Zhang, Xuyuan Li, Yicheng Gu, Yuancheng Wang, Zengqiang Shang, Zhizheng Wu","submitted_at":"2024-07-07T13:24:54Z","abstract_excerpt":"Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech remains a challenge due to the scarcity of large, diverse, and spontaneous speech datasets. In response, we introduce Emilia, the first large-scale, multilingual, and diverse speech generation dataset. Emilia starts with over 101k hours of speech across six languages, covering a wide range of speaking styles to enable more natural and spontaneous speech generation. To facilitate the scale-up of Emilia, we also present E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05361","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/2407.05361/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":"2407.05361","created_at":"2026-07-05T09:04:11.096163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05361v3","created_at":"2026-07-05T09:04:11.096163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05361","created_at":"2026-07-05T09:04:11.096163+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6PJYWIAU3RL","created_at":"2026-07-05T09:04:11.096163+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6PJYWIAU3RLQZTN","created_at":"2026-07-05T09:04:11.096163+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6PJYWIA","created_at":"2026-07-05T09:04:11.096163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09048","citing_title":"BareWave: Waveform-Native Flow-Matching Text-to-Speech","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10029","citing_title":"Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30748","citing_title":"Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25659","citing_title":"StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration","ref_index":10,"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":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P","json":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P.json","graph_json":"https://pith.science/api/pith-number/X6PJYWIAU3RLQZTN26VSKQ7M5P/graph.json","events_json":"https://pith.science/api/pith-number/X6PJYWIAU3RLQZTN26VSKQ7M5P/events.json","paper":"https://pith.science/paper/X6PJYWIA"},"agent_actions":{"view_html":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P","download_json":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P.json","view_paper":"https://pith.science/paper/X6PJYWIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05361&json=true","fetch_graph":"https://pith.science/api/pith-number/X6PJYWIAU3RLQZTN26VSKQ7M5P/graph.json","fetch_events":"https://pith.science/api/pith-number/X6PJYWIAU3RLQZTN26VSKQ7M5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P/action/storage_attestation","attest_author":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P/action/author_attestation","sign_citation":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P/action/citation_signature","submit_replication":"https://pith.science/pith/X6PJYWIAU3RLQZTN26VSKQ7M5P/action/replication_record"}},"created_at":"2026-07-05T09:04:11.096163+00:00","updated_at":"2026-07-05T09:04:11.096163+00:00"}