{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R4ZFCRJRSUS2A74L2XHFM2STNN","short_pith_number":"pith:R4ZFCRJR","schema_version":"1.0","canonical_sha256":"8f325145319525a07f8bd5ce566a536b6d4f5d62f363dfd33949281b77ebf844","source":{"kind":"arxiv","id":"2010.11567","version":2},"attestation_state":"computed","paper":{"title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hui Bu, Ming Li, Shaoji Zhang, Xin Xu, Yao Shi","submitted_at":"2020-10-22T09:54:22Z","abstract_excerpt":"In this paper, we present AISHELL-3, a large-scale and high-fidelity multi-speaker Mandarin speech corpus which could be used to train multi-speaker Text-to-Speech (TTS) systems. The corpus contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Accordingly, transcripts in Chinese character-level and pinyin-level are provided along with the recordings. We present a baseline system that uses AISHELL-3 for multi-speaker Madarin "},"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":"2010.11567","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-10-22T09:54:22Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"de0b30ca3f0ff3049a751c80d743902fdbe6075ea928a13f0081b8aa7f55ad3d","abstract_canon_sha256":"5b0143f221d5e56bcc6041c388d860f05e9f1cddd546dd25e0a374d9cef53c3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:09.801762Z","signature_b64":"5gTu5mwqRdlmMpmJ9xDaJGklQoGnl2MfDOBVLBNM6Sd6vaB7IgLY9/EeaT883msioZ1PyGOuKkvobHKiReScBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f325145319525a07f8bd5ce566a536b6d4f5d62f363dfd33949281b77ebf844","last_reissued_at":"2026-07-05T02:34:09.801344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:09.801344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hui Bu, Ming Li, Shaoji Zhang, Xin Xu, Yao Shi","submitted_at":"2020-10-22T09:54:22Z","abstract_excerpt":"In this paper, we present AISHELL-3, a large-scale and high-fidelity multi-speaker Mandarin speech corpus which could be used to train multi-speaker Text-to-Speech (TTS) systems. The corpus contains roughly 85 hours of emotion-neutral recordings spoken by 218 native Chinese mandarin speakers. Their auxiliary attributes such as gender, age group and native accents are explicitly marked and provided in the corpus. Accordingly, transcripts in Chinese character-level and pinyin-level are provided along with the recordings. We present a baseline system that uses AISHELL-3 for multi-speaker Madarin "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11567","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/2010.11567/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":"2010.11567","created_at":"2026-07-05T02:34:09.801406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11567v2","created_at":"2026-07-05T02:34:09.801406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11567","created_at":"2026-07-05T02:34:09.801406+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4ZFCRJRSUS2","created_at":"2026-07-05T02:34:09.801406+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4ZFCRJRSUS2A74L","created_at":"2026-07-05T02:34:09.801406+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4ZFCRJR","created_at":"2026-07-05T02:34:09.801406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21457","citing_title":"DisSpeech: Low-Resource Controllable Mandarin Stuttered Speech Synthesis for ASR Augmentation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11631","citing_title":"Benchmarking Neural Speech Compression from a Rate-Distortion Perspective","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11681","citing_title":"UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10591","citing_title":"ContextCodec: Content-Focused Context Guidance for Ultra-Low Bitrate Speech Coding","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04418","citing_title":"CleanCodec: Efficient and Robust Speech Tokenization via Perceptually Guided Encoding","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01804","citing_title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19883","citing_title":"CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2512.20211","citing_title":"Aliasing-Free Neural Audio Synthesis","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04638","citing_title":"SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11098","citing_title":"AffectCodec: Emotion-Preserving Neural Speech Codec for Expressive Speech Modeling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18425","citing_title":"Kimi-Audio Technical Report","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08184","citing_title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":129,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN","json":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN.json","graph_json":"https://pith.science/api/pith-number/R4ZFCRJRSUS2A74L2XHFM2STNN/graph.json","events_json":"https://pith.science/api/pith-number/R4ZFCRJRSUS2A74L2XHFM2STNN/events.json","paper":"https://pith.science/paper/R4ZFCRJR"},"agent_actions":{"view_html":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN","download_json":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN.json","view_paper":"https://pith.science/paper/R4ZFCRJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11567&json=true","fetch_graph":"https://pith.science/api/pith-number/R4ZFCRJRSUS2A74L2XHFM2STNN/graph.json","fetch_events":"https://pith.science/api/pith-number/R4ZFCRJRSUS2A74L2XHFM2STNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN/action/storage_attestation","attest_author":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN/action/author_attestation","sign_citation":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN/action/citation_signature","submit_replication":"https://pith.science/pith/R4ZFCRJRSUS2A74L2XHFM2STNN/action/replication_record"}},"created_at":"2026-07-05T02:34:09.801406+00:00","updated_at":"2026-07-05T02:34:09.801406+00:00"}