{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GUTNM4GGJIKS7OCIU4NCJVQMYP","short_pith_number":"pith:GUTNM4GG","schema_version":"1.0","canonical_sha256":"3526d670c64a152fb848a71a24d60cc3e285dec0f2a3f55b16eeacb6d72f224a","source":{"kind":"arxiv","id":"2203.15873","version":1},"attestation_state":"computed","paper":{"title":"An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Ilhan Aslan, Meishu Song, Xin Jing, Zijiang Yang","submitted_at":"2022-03-29T19:41:34Z","abstract_excerpt":"Emotional voice conversion (EVC) focuses on converting a speech utterance from a source to a target emotion; it can thus be a key enabling technology for human-computer interaction applications and beyond. However, EVC remains an unsolved research problem with several challenges. In particular, as speech rate and rhythm are two key factors of emotional conversion, models have to generate output sequences of differing length. Sequence-to-sequence modelling is recently emerging as a competitive paradigm for models that can overcome those challenges. In an attempt to stimulate further research in"},"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":"2203.15873","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-03-29T19:41:34Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8fde5ef5ba1aceb6cb1485247fcffbf5ce5035ba59187c91d50e49dc29e95c6a","abstract_canon_sha256":"58657949bae397fb1f4f656331d9af29845fe8686248357cc5d144b313fd39f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:04.572583Z","signature_b64":"WJ8Gl/KRhmGC+4XM0CTmW0X3lI1Sn8TcB8VJhyj+orgG5ydnAg398Z5Uc/3ApGBaCRjC3iGr5q7ZhUFLv1AzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3526d670c64a152fb848a71a24d60cc3e285dec0f2a3f55b16eeacb6d72f224a","last_reissued_at":"2026-07-05T04:10:04.572085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:04.572085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Ilhan Aslan, Meishu Song, Xin Jing, Zijiang Yang","submitted_at":"2022-03-29T19:41:34Z","abstract_excerpt":"Emotional voice conversion (EVC) focuses on converting a speech utterance from a source to a target emotion; it can thus be a key enabling technology for human-computer interaction applications and beyond. However, EVC remains an unsolved research problem with several challenges. In particular, as speech rate and rhythm are two key factors of emotional conversion, models have to generate output sequences of differing length. Sequence-to-sequence modelling is recently emerging as a competitive paradigm for models that can overcome those challenges. In an attempt to stimulate further research in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15873","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/2203.15873/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":"2203.15873","created_at":"2026-07-05T04:10:04.572147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15873v1","created_at":"2026-07-05T04:10:04.572147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15873","created_at":"2026-07-05T04:10:04.572147+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUTNM4GGJIKS","created_at":"2026-07-05T04:10:04.572147+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUTNM4GGJIKS7OCI","created_at":"2026-07-05T04:10:04.572147+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUTNM4GG","created_at":"2026-07-05T04:10:04.572147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24794","citing_title":"V.O.I.C.E (Voice, Ownership, Identity, Control, Expression): Risk Taxonomy of Synthetic Voice Generation From Empirical Data","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP","json":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP.json","graph_json":"https://pith.science/api/pith-number/GUTNM4GGJIKS7OCIU4NCJVQMYP/graph.json","events_json":"https://pith.science/api/pith-number/GUTNM4GGJIKS7OCIU4NCJVQMYP/events.json","paper":"https://pith.science/paper/GUTNM4GG"},"agent_actions":{"view_html":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP","download_json":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP.json","view_paper":"https://pith.science/paper/GUTNM4GG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15873&json=true","fetch_graph":"https://pith.science/api/pith-number/GUTNM4GGJIKS7OCIU4NCJVQMYP/graph.json","fetch_events":"https://pith.science/api/pith-number/GUTNM4GGJIKS7OCIU4NCJVQMYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP/action/storage_attestation","attest_author":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP/action/author_attestation","sign_citation":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP/action/citation_signature","submit_replication":"https://pith.science/pith/GUTNM4GGJIKS7OCIU4NCJVQMYP/action/replication_record"}},"created_at":"2026-07-05T04:10:04.572147+00:00","updated_at":"2026-07-05T04:10:04.572147+00:00"}