{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PHZXMA35MOTSEJ2HEIDRHL2ODC","short_pith_number":"pith:PHZXMA35","schema_version":"1.0","canonical_sha256":"79f376037d63a7222747220713af4e18984ce8757f1b58b1de2277095548a02c","source":{"kind":"arxiv","id":"2205.04029","version":2},"attestation_state":"computed","paper":{"title":"Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Frank Xu, Huazhe Li, Jiatong Shi, Nan Huo, Peter Wu, Qin Jin, Shinji Watanabe, Shuai Guo, Tao Qian, Tomoki Hayashi, Xuankai Chang, Yuning Wu","submitted_at":"2022-05-09T04:25:47Z","abstract_excerpt":"This paper introduces a new open-source platform named Muskits for end-to-end music processing, which mainly focuses on end-to-end singing voice synthesis (E2E-SVS). Muskits supports state-of-the-art SVS models, including RNN SVS, transformer SVS, and XiaoiceSing. The design of Muskits follows the style of widely-used speech processing toolkits, ESPnet and Kaldi, for data prepossessing, training, and recipe pipelines. To the best of our knowledge, this toolkit is the first platform that allows a fair and highly-reproducible comparison between several published works in SVS. In addition, we als"},"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":"2205.04029","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-05-09T04:25:47Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"a2bf14c6b6dd1a97ffb2268c2c137ff00a44337cd07b4c2d9c3b5e826170a46c","abstract_canon_sha256":"f5edf0651d9c8deed27c655c287ffd5993839e6c59bcf92a86ed5211e7c75322"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:49.213497Z","signature_b64":"7QOJEDPQlTH5Lnbu2jVqGTw4iVZapNTODq38qLqlq6JcrGh3k/KI5qqw1D2sNZf3bxK1A2IegU54kjT0PCTkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f376037d63a7222747220713af4e18984ce8757f1b58b1de2277095548a02c","last_reissued_at":"2026-07-05T04:36:49.213033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:49.213033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Frank Xu, Huazhe Li, Jiatong Shi, Nan Huo, Peter Wu, Qin Jin, Shinji Watanabe, Shuai Guo, Tao Qian, Tomoki Hayashi, Xuankai Chang, Yuning Wu","submitted_at":"2022-05-09T04:25:47Z","abstract_excerpt":"This paper introduces a new open-source platform named Muskits for end-to-end music processing, which mainly focuses on end-to-end singing voice synthesis (E2E-SVS). Muskits supports state-of-the-art SVS models, including RNN SVS, transformer SVS, and XiaoiceSing. The design of Muskits follows the style of widely-used speech processing toolkits, ESPnet and Kaldi, for data prepossessing, training, and recipe pipelines. To the best of our knowledge, this toolkit is the first platform that allows a fair and highly-reproducible comparison between several published works in SVS. In addition, we als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04029","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/2205.04029/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":"2205.04029","created_at":"2026-07-05T04:36:49.213083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04029v2","created_at":"2026-07-05T04:36:49.213083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04029","created_at":"2026-07-05T04:36:49.213083+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHZXMA35MOTS","created_at":"2026-07-05T04:36:49.213083+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHZXMA35MOTSEJ2H","created_at":"2026-07-05T04:36:49.213083+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHZXMA35","created_at":"2026-07-05T04:36:49.213083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30366","citing_title":"Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC","json":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC.json","graph_json":"https://pith.science/api/pith-number/PHZXMA35MOTSEJ2HEIDRHL2ODC/graph.json","events_json":"https://pith.science/api/pith-number/PHZXMA35MOTSEJ2HEIDRHL2ODC/events.json","paper":"https://pith.science/paper/PHZXMA35"},"agent_actions":{"view_html":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC","download_json":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC.json","view_paper":"https://pith.science/paper/PHZXMA35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04029&json=true","fetch_graph":"https://pith.science/api/pith-number/PHZXMA35MOTSEJ2HEIDRHL2ODC/graph.json","fetch_events":"https://pith.science/api/pith-number/PHZXMA35MOTSEJ2HEIDRHL2ODC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC/action/storage_attestation","attest_author":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC/action/author_attestation","sign_citation":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC/action/citation_signature","submit_replication":"https://pith.science/pith/PHZXMA35MOTSEJ2HEIDRHL2ODC/action/replication_record"}},"created_at":"2026-07-05T04:36:49.213083+00:00","updated_at":"2026-07-05T04:36:49.213083+00:00"}