{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H7MEGV3MEU7UFJQNLJC2UZEZVC","short_pith_number":"pith:H7MEGV3M","schema_version":"1.0","canonical_sha256":"3fd843576c253f42a60d5a45aa6499a8be4c5d74cd0f20b52b8b80028ce5d340","source":{"kind":"arxiv","id":"2206.11558","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Gyeong-Hoon Lee, Min-Su Kang, Tae-Woo Kim","submitted_at":"2022-06-23T09:11:02Z","abstract_excerpt":"Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the meaning of each feature is explicitly distinguished. Another approach is to predict mel-spectrograms for a neural vocoder. However, parametric vocoders have limitations of voice quality and the mel-spectrogram features are difficult to model because the timbre and pitch information are entangled. In this study, we propose a singing voice synthesis model with "},"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":"2206.11558","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-06-23T09:11:02Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"14d1039e0a8ba25ab64cdce9e36e2b66a412671b54c67b2cade354b70915f7e8","abstract_canon_sha256":"7099b933511ef823b03dc2184b41ceac22accea6850a66d0429e2a4ac7030000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:02.005531Z","signature_b64":"1apWbnFWuUnL0T914lMEOAVqy4U+EXINSrVK8ZU1ebkH5ATxWH0S3brQxjEaWGusw2hFHpsnLL1Wj5Ny9600Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd843576c253f42a60d5a45aa6499a8be4c5d74cd0f20b52b8b80028ce5d340","last_reissued_at":"2026-07-05T08:31:02.005101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:02.005101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Gyeong-Hoon Lee, Min-Su Kang, Tae-Woo Kim","submitted_at":"2022-06-23T09:11:02Z","abstract_excerpt":"Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the meaning of each feature is explicitly distinguished. Another approach is to predict mel-spectrograms for a neural vocoder. However, parametric vocoders have limitations of voice quality and the mel-spectrogram features are difficult to model because the timbre and pitch information are entangled. In this study, we propose a singing voice synthesis model with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11558","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/2206.11558/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":"2206.11558","created_at":"2026-07-05T08:31:02.005157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11558v2","created_at":"2026-07-05T08:31:02.005157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11558","created_at":"2026-07-05T08:31:02.005157+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7MEGV3MEU7U","created_at":"2026-07-05T08:31:02.005157+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7MEGV3MEU7UFJQN","created_at":"2026-07-05T08:31:02.005157+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7MEGV3M","created_at":"2026-07-05T08:31:02.005157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21478","citing_title":"SmoothSinger: A Conditional Diffusion Model for Singing Voice Synthesis with Multi-Resolution Architecture","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC","json":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC.json","graph_json":"https://pith.science/api/pith-number/H7MEGV3MEU7UFJQNLJC2UZEZVC/graph.json","events_json":"https://pith.science/api/pith-number/H7MEGV3MEU7UFJQNLJC2UZEZVC/events.json","paper":"https://pith.science/paper/H7MEGV3M"},"agent_actions":{"view_html":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC","download_json":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC.json","view_paper":"https://pith.science/paper/H7MEGV3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11558&json=true","fetch_graph":"https://pith.science/api/pith-number/H7MEGV3MEU7UFJQNLJC2UZEZVC/graph.json","fetch_events":"https://pith.science/api/pith-number/H7MEGV3MEU7UFJQNLJC2UZEZVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC/action/storage_attestation","attest_author":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC/action/author_attestation","sign_citation":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC/action/citation_signature","submit_replication":"https://pith.science/pith/H7MEGV3MEU7UFJQNLJC2UZEZVC/action/replication_record"}},"created_at":"2026-07-05T08:31:02.005157+00:00","updated_at":"2026-07-05T08:31:02.005157+00:00"}