{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3BQZLXEUGHDW4JNIDMMGBYJQPT","short_pith_number":"pith:3BQZLXEU","schema_version":"1.0","canonical_sha256":"d86195dc9431c76e25a81b1860e1307cdef22bf2939f98940d7d41af057b8b92","source":{"kind":"arxiv","id":"2006.06261","version":1},"attestation_state":"computed","paper":{"title":"XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Luan, Jie Wu, Li Zhou, Peiling Lu, Xu Tan","submitted_at":"2020-06-11T09:09:59Z","abstract_excerpt":"This paper presents XiaoiceSing, a high-quality singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. We follow the main architecture of FastSpeech while proposing some singing-specific design: 1) Besides phoneme ID and position encoding, features from musical score (e.g.note pitch and length) are also added. 2) To attenuate off-key issues, we add a residual connection in F0 prediction. 3) In addition to the duration loss of each phoneme, the duration of all the phonemes in a musical note is accumulated to calculate the syllable duration los"},"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":"2006.06261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-11T09:09:59Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"43a33a5330ab809706d583b03bb74ae206b9ad061e014caa027898cfc69dbcf1","abstract_canon_sha256":"d740a8d4dedd9316f8739d32c192f98068402a17151638a1f865f4887578e256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:32.266808Z","signature_b64":"P6yamwcZC/t6Zcgdt86GIxhAw3ZLL0Z66BOgwRQTuANA7NX9tUzaS3xOEZaH+Jd8u1eAXb9MfNARj1BrVlmaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d86195dc9431c76e25a81b1860e1307cdef22bf2939f98940d7d41af057b8b92","last_reissued_at":"2026-07-05T01:09:32.266387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:32.266387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Luan, Jie Wu, Li Zhou, Peiling Lu, Xu Tan","submitted_at":"2020-06-11T09:09:59Z","abstract_excerpt":"This paper presents XiaoiceSing, a high-quality singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. We follow the main architecture of FastSpeech while proposing some singing-specific design: 1) Besides phoneme ID and position encoding, features from musical score (e.g.note pitch and length) are also added. 2) To attenuate off-key issues, we add a residual connection in F0 prediction. 3) In addition to the duration loss of each phoneme, the duration of all the phonemes in a musical note is accumulated to calculate the syllable duration los"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06261","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/2006.06261/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":"2006.06261","created_at":"2026-07-05T01:09:32.266447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.06261v1","created_at":"2026-07-05T01:09:32.266447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06261","created_at":"2026-07-05T01:09:32.266447+00:00"},{"alias_kind":"pith_short_12","alias_value":"3BQZLXEUGHDW","created_at":"2026-07-05T01:09:32.266447+00:00"},{"alias_kind":"pith_short_16","alias_value":"3BQZLXEUGHDW4JNI","created_at":"2026-07-05T01:09:32.266447+00:00"},{"alias_kind":"pith_short_8","alias_value":"3BQZLXEU","created_at":"2026-07-05T01:09:32.266447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30580","citing_title":"MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT","json":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT.json","graph_json":"https://pith.science/api/pith-number/3BQZLXEUGHDW4JNIDMMGBYJQPT/graph.json","events_json":"https://pith.science/api/pith-number/3BQZLXEUGHDW4JNIDMMGBYJQPT/events.json","paper":"https://pith.science/paper/3BQZLXEU"},"agent_actions":{"view_html":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT","download_json":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT.json","view_paper":"https://pith.science/paper/3BQZLXEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.06261&json=true","fetch_graph":"https://pith.science/api/pith-number/3BQZLXEUGHDW4JNIDMMGBYJQPT/graph.json","fetch_events":"https://pith.science/api/pith-number/3BQZLXEUGHDW4JNIDMMGBYJQPT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT/action/storage_attestation","attest_author":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT/action/author_attestation","sign_citation":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT/action/citation_signature","submit_replication":"https://pith.science/pith/3BQZLXEUGHDW4JNIDMMGBYJQPT/action/replication_record"}},"created_at":"2026-07-05T01:09:32.266447+00:00","updated_at":"2026-07-05T01:09:32.266447+00:00"}