{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SEF73PGCIUBBXYDTMOPBXNUCFP","short_pith_number":"pith:SEF73PGC","schema_version":"1.0","canonical_sha256":"910bfdbcc245021be073639e1bb6822bf4d0bca623bab4ee6e02e7d0a7ccd543","source":{"kind":"arxiv","id":"1806.09514","version":1},"attestation_state":"computed","paper":{"title":"The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adaeze Adigwe, Kevin El Haddad, No\\'e Tits, Sarah Ostadabbas, Thierry Dutoit","submitted_at":"2018-06-25T15:01:54Z","abstract_excerpt":"In this paper, we present a database of emotional speech intended to be open-sourced and used for synthesis and generation purpose. It contains data for male and female actors in English and a male actor in French. The database covers 5 emotion classes so it could be suitable to build synthesis and voice transformation systems with the potential to control the emotional dimension in a continuous way. We show the data's efficiency by building a simple MLP system converting neutral to angry speech style and evaluate it via a CMOS perception test. Even though the system is a very simple one, the "},"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":"1806.09514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-25T15:01:54Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"538c6e547f75c4b00028caeae6cb37a380fda7dab5f54ee2ecfe348c1fc817f9","abstract_canon_sha256":"d49845e12b5f79b2aabdeec438099347e91bec21304e5a7e29358872dc0e72c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:25.583144Z","signature_b64":"OUmJDo++2ZUr3l4VpfuaMJRnixxSvKzv3ASADYKshI5Qs4DRmXl0k9olxf2ckP/VLGWK+Y/90YgXxQ0eX/M0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"910bfdbcc245021be073639e1bb6822bf4d0bca623bab4ee6e02e7d0a7ccd543","last_reissued_at":"2026-05-18T00:12:25.582633Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:25.582633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adaeze Adigwe, Kevin El Haddad, No\\'e Tits, Sarah Ostadabbas, Thierry Dutoit","submitted_at":"2018-06-25T15:01:54Z","abstract_excerpt":"In this paper, we present a database of emotional speech intended to be open-sourced and used for synthesis and generation purpose. It contains data for male and female actors in English and a male actor in French. The database covers 5 emotion classes so it could be suitable to build synthesis and voice transformation systems with the potential to control the emotional dimension in a continuous way. We show the data's efficiency by building a simple MLP system converting neutral to angry speech style and evaluate it via a CMOS perception test. Even though the system is a very simple one, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.09514","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":""},"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":"1806.09514","created_at":"2026-05-18T00:12:25.582712+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.09514v1","created_at":"2026-05-18T00:12:25.582712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.09514","created_at":"2026-05-18T00:12:25.582712+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEF73PGCIUBB","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEF73PGCIUBBXYDT","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEF73PGC","created_at":"2026-05-18T12:32:53.628368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.02784","citing_title":"A Methodology for Controlling the Emotional Expressiveness in Synthetic Speech -- a Deep Learning approach","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20830","citing_title":"Raon-OpenTTS: Open Models and Data for Robust Text-to-Speech","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2509.22220","citing_title":"StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2301.02111","citing_title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13335","citing_title":"SEDTalker: Emotion-Aware 3D Facial Animation Using Frame-Level Speech Emotion Diarization","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP","json":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP.json","graph_json":"https://pith.science/api/pith-number/SEF73PGCIUBBXYDTMOPBXNUCFP/graph.json","events_json":"https://pith.science/api/pith-number/SEF73PGCIUBBXYDTMOPBXNUCFP/events.json","paper":"https://pith.science/paper/SEF73PGC"},"agent_actions":{"view_html":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP","download_json":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP.json","view_paper":"https://pith.science/paper/SEF73PGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.09514&json=true","fetch_graph":"https://pith.science/api/pith-number/SEF73PGCIUBBXYDTMOPBXNUCFP/graph.json","fetch_events":"https://pith.science/api/pith-number/SEF73PGCIUBBXYDTMOPBXNUCFP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP/action/storage_attestation","attest_author":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP/action/author_attestation","sign_citation":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP/action/citation_signature","submit_replication":"https://pith.science/pith/SEF73PGCIUBBXYDTMOPBXNUCFP/action/replication_record"}},"created_at":"2026-05-18T00:12:25.582712+00:00","updated_at":"2026-05-18T00:12:25.582712+00:00"}