{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B34G4YC2O3MQOG333V7DMTOIN3","short_pith_number":"pith:B34G4YC2","schema_version":"1.0","canonical_sha256":"0ef86e605a76d9071b7bdd7e364dc86ee40e9eb8797558c5e9188149f9a93308","source":{"kind":"arxiv","id":"2106.09317","version":1},"attestation_state":"computed","paper":{"title":"EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenye Cui, Feiyang Chen, Jinglin Liu, Ming Lei, Rongjie Huang, Yi Ren, Zhou Zhao","submitted_at":"2021-06-17T08:34:21Z","abstract_excerpt":"Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to generate a more emotional and more expressive speech is becoming a new challenge to researchers due to the scarcity of high-quality emotion speech dataset and the lack of advanced emotional TTS model. In this paper, we first briefly introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. After that, we propose a simple but ef"},"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":"2106.09317","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T08:34:21Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a92ed0a3027a831163d479718612abe4ae8a0e7ab8acc724b4c74cf53afc7a3f","abstract_canon_sha256":"45deba176ed2d34019fadeb32461d9232a551d6692f4fd3fc2a608abca9a53c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:51:54.755129Z","signature_b64":"FxoTMCrjl+Y5dLk6dwJr3ZxBtOpvGZYK6HuABEqCsXv1do4dR14oeENGZPiS3qpjGYn+PP+f2Jb02Xx1BrH+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ef86e605a76d9071b7bdd7e364dc86ee40e9eb8797558c5e9188149f9a93308","last_reissued_at":"2026-07-05T02:51:54.754715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:51:54.754715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMOVIE: A Mandarin Emotion Speech Dataset with a Simple Emotional Text-to-Speech Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenye Cui, Feiyang Chen, Jinglin Liu, Ming Lei, Rongjie Huang, Yi Ren, Zhou Zhao","submitted_at":"2021-06-17T08:34:21Z","abstract_excerpt":"Recently, there has been an increasing interest in neural speech synthesis. While the deep neural network achieves the state-of-the-art result in text-to-speech (TTS) tasks, how to generate a more emotional and more expressive speech is becoming a new challenge to researchers due to the scarcity of high-quality emotion speech dataset and the lack of advanced emotional TTS model. In this paper, we first briefly introduce and publicly release a Mandarin emotion speech dataset including 9,724 samples with audio files and its emotion human-labeled annotation. After that, we propose a simple but ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09317","kind":"arxiv","version":1},"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/2106.09317/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":"2106.09317","created_at":"2026-07-05T02:51:54.754773+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09317v1","created_at":"2026-07-05T02:51:54.754773+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09317","created_at":"2026-07-05T02:51:54.754773+00:00"},{"alias_kind":"pith_short_12","alias_value":"B34G4YC2O3MQ","created_at":"2026-07-05T02:51:54.754773+00:00"},{"alias_kind":"pith_short_16","alias_value":"B34G4YC2O3MQOG33","created_at":"2026-07-05T02:51:54.754773+00:00"},{"alias_kind":"pith_short_8","alias_value":"B34G4YC2","created_at":"2026-07-05T02:51:54.754773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3","json":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3.json","graph_json":"https://pith.science/api/pith-number/B34G4YC2O3MQOG333V7DMTOIN3/graph.json","events_json":"https://pith.science/api/pith-number/B34G4YC2O3MQOG333V7DMTOIN3/events.json","paper":"https://pith.science/paper/B34G4YC2"},"agent_actions":{"view_html":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3","download_json":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3.json","view_paper":"https://pith.science/paper/B34G4YC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09317&json=true","fetch_graph":"https://pith.science/api/pith-number/B34G4YC2O3MQOG333V7DMTOIN3/graph.json","fetch_events":"https://pith.science/api/pith-number/B34G4YC2O3MQOG333V7DMTOIN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3/action/storage_attestation","attest_author":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3/action/author_attestation","sign_citation":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3/action/citation_signature","submit_replication":"https://pith.science/pith/B34G4YC2O3MQOG333V7DMTOIN3/action/replication_record"}},"created_at":"2026-07-05T02:51:54.754773+00:00","updated_at":"2026-07-05T02:51:54.754773+00:00"}