{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LWWRRWKSXK6SEAB6UMYRJE2IUK","short_pith_number":"pith:LWWRRWKS","schema_version":"1.0","canonical_sha256":"5dad18d952babd22003ea331149348a2b95543080319e3b38f365b94d651284d","source":{"kind":"arxiv","id":"1910.03713","version":2},"attestation_state":"computed","paper":{"title":"MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Marco Pasini","submitted_at":"2019-10-08T23:22:50Z","abstract_excerpt":"Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method that relies on non-parallel speech data and is able to convert audio signals of arbitrary length from a source voice to a target voice. We firstly compute spectrograms from waveform data and then perform a domain translation using a Generative Adversarial Network (GAN) architecture. An additional siamese network helps preserving speech information in the trans"},"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":"1910.03713","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-10-08T23:22:50Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"2c17a28c204c297c468e93dfa810f437d5b77b05022ac6e8dc8ed0be91841059","abstract_canon_sha256":"3cf1034ec1d898155cd6e3b3814c5e658250239637336552b21fdf6df7fd6e11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:09.996101Z","signature_b64":"cVnQo5hJGzqMP23oJa+esJfu3xd9/hPQ4Se8Oup7zd4lDkpmBpU0E+IRoRI5yL8K9ii8qzIIw7IQ1iE6ShE9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5dad18d952babd22003ea331149348a2b95543080319e3b38f365b94d651284d","last_reissued_at":"2026-07-05T00:24:09.995731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:09.995731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MelGAN-VC: Voice Conversion and Audio Style Transfer on arbitrarily long samples using Spectrograms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Marco Pasini","submitted_at":"2019-10-08T23:22:50Z","abstract_excerpt":"Traditional voice conversion methods rely on parallel recordings of multiple speakers pronouncing the same sentences. For real-world applications however, parallel data is rarely available. We propose MelGAN-VC, a voice conversion method that relies on non-parallel speech data and is able to convert audio signals of arbitrary length from a source voice to a target voice. We firstly compute spectrograms from waveform data and then perform a domain translation using a Generative Adversarial Network (GAN) architecture. An additional siamese network helps preserving speech information in the trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03713","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/1910.03713/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":"1910.03713","created_at":"2026-07-05T00:24:09.995788+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.03713v2","created_at":"2026-07-05T00:24:09.995788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03713","created_at":"2026-07-05T00:24:09.995788+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWWRRWKSXK6S","created_at":"2026-07-05T00:24:09.995788+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWWRRWKSXK6SEAB6","created_at":"2026-07-05T00:24:09.995788+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWWRRWKS","created_at":"2026-07-05T00:24:09.995788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18075","citing_title":"Music2Fail: Transfer Music to Failed Recorder Style","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK","json":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK.json","graph_json":"https://pith.science/api/pith-number/LWWRRWKSXK6SEAB6UMYRJE2IUK/graph.json","events_json":"https://pith.science/api/pith-number/LWWRRWKSXK6SEAB6UMYRJE2IUK/events.json","paper":"https://pith.science/paper/LWWRRWKS"},"agent_actions":{"view_html":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK","download_json":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK.json","view_paper":"https://pith.science/paper/LWWRRWKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.03713&json=true","fetch_graph":"https://pith.science/api/pith-number/LWWRRWKSXK6SEAB6UMYRJE2IUK/graph.json","fetch_events":"https://pith.science/api/pith-number/LWWRRWKSXK6SEAB6UMYRJE2IUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK/action/storage_attestation","attest_author":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK/action/author_attestation","sign_citation":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK/action/citation_signature","submit_replication":"https://pith.science/pith/LWWRRWKSXK6SEAB6UMYRJE2IUK/action/replication_record"}},"created_at":"2026-07-05T00:24:09.995788+00:00","updated_at":"2026-07-05T00:24:09.995788+00:00"}