{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5XBNNBTPHXTBC2ANPOKH3MYJTA","short_pith_number":"pith:5XBNNBTP","schema_version":"1.0","canonical_sha256":"edc2d6866f3de611680d7b947db309983c52521b6b11bab49b762c6477d92ef2","source":{"kind":"arxiv","id":"2409.07226","version":2},"attestation_state":"computed","paper":{"title":"Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiatong Shi, Jionghao Han, Qin Jin, Shinji Watanabe, Tao Qian, Xinyi Bai, Yifeng Yu, Yueqian Lin, Yuning Wu, Yuxun Tang","submitted_at":"2024-09-11T12:36:13Z","abstract_excerpt":"This research presents Muskits-ESPnet, a versatile toolkit that introduces new paradigms to Singing Voice Synthesis (SVS) through the application of pretrained audio models in both continuous and discrete approaches. Specifically, we explore discrete representations derived from SSL models and audio codecs and offer significant advantages in versatility and intelligence, supporting multi-format inputs and adaptable data processing workflows for various SVS models. The toolkit features automatic music score error detection and correction, as well as a perception auto-evaluation module to imitat"},"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":"2409.07226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T12:36:13Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f0b208c3ebd070d4016781cae2602b291de00792ff6c2327a8ccf99dcbfb0f84","abstract_canon_sha256":"92093767bfbad04aab9db08ff820e8970adf09ab8d5873413b0724e9e33c0213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:53.930285Z","signature_b64":"p4B371+N53zoaNj0q4tK6fKNbHgdR4OBQuVpvwtlt/gmp0RrD9OAZLv5UypbHdnCn8rJ6b0OeeJ9M+LnNqsGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc2d6866f3de611680d7b947db309983c52521b6b11bab49b762c6477d92ef2","last_reissued_at":"2026-07-05T09:18:53.929814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:53.929814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiatong Shi, Jionghao Han, Qin Jin, Shinji Watanabe, Tao Qian, Xinyi Bai, Yifeng Yu, Yueqian Lin, Yuning Wu, Yuxun Tang","submitted_at":"2024-09-11T12:36:13Z","abstract_excerpt":"This research presents Muskits-ESPnet, a versatile toolkit that introduces new paradigms to Singing Voice Synthesis (SVS) through the application of pretrained audio models in both continuous and discrete approaches. Specifically, we explore discrete representations derived from SSL models and audio codecs and offer significant advantages in versatility and intelligence, supporting multi-format inputs and adaptable data processing workflows for various SVS models. The toolkit features automatic music score error detection and correction, as well as a perception auto-evaluation module to imitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07226","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/2409.07226/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":"2409.07226","created_at":"2026-07-05T09:18:53.929873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07226v2","created_at":"2026-07-05T09:18:53.929873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07226","created_at":"2026-07-05T09:18:53.929873+00:00"},{"alias_kind":"pith_short_12","alias_value":"5XBNNBTPHXTB","created_at":"2026-07-05T09:18:53.929873+00:00"},{"alias_kind":"pith_short_16","alias_value":"5XBNNBTPHXTBC2AN","created_at":"2026-07-05T09:18:53.929873+00:00"},{"alias_kind":"pith_short_8","alias_value":"5XBNNBTP","created_at":"2026-07-05T09:18:53.929873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA","json":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA.json","graph_json":"https://pith.science/api/pith-number/5XBNNBTPHXTBC2ANPOKH3MYJTA/graph.json","events_json":"https://pith.science/api/pith-number/5XBNNBTPHXTBC2ANPOKH3MYJTA/events.json","paper":"https://pith.science/paper/5XBNNBTP"},"agent_actions":{"view_html":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA","download_json":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA.json","view_paper":"https://pith.science/paper/5XBNNBTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07226&json=true","fetch_graph":"https://pith.science/api/pith-number/5XBNNBTPHXTBC2ANPOKH3MYJTA/graph.json","fetch_events":"https://pith.science/api/pith-number/5XBNNBTPHXTBC2ANPOKH3MYJTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA/action/storage_attestation","attest_author":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA/action/author_attestation","sign_citation":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA/action/citation_signature","submit_replication":"https://pith.science/pith/5XBNNBTPHXTBC2ANPOKH3MYJTA/action/replication_record"}},"created_at":"2026-07-05T09:18:53.929873+00:00","updated_at":"2026-07-05T09:18:53.929873+00:00"}