{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENWREVHZRJ42O2ZG5IXXE3WJZV","short_pith_number":"pith:ENWREVHZ","schema_version":"1.0","canonical_sha256":"236d1254f98a79a76b26ea2f726ec9cd46ad4484b6c87573c78736655f250739","source":{"kind":"arxiv","id":"2507.08530","version":1},"attestation_state":"computed","paper":{"title":"MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"George Fazekas, Geraint Wiggins, Jingjing Tang, Junichi Yamagishi, Xin Wang, Zhe Zhang","submitted_at":"2025-07-11T12:28:20Z","abstract_excerpt":"Generating expressive audio performances from music scores requires models to capture both instrument acoustics and human interpretation. Traditional music performance synthesis pipelines follow a two-stage approach, first generating expressive performance MIDI from a score, then synthesising the MIDI into audio. However, the synthesis models often struggle to generalise across diverse MIDI sources, musical styles, and recording environments. To address these challenges, we propose MIDI-VALLE, a neural codec language model adapted from the VALLE framework, which was originally designed for zer"},"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":"2507.08530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-11T12:28:20Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"1535b9263eb2eeb5064f4280b3cb8c9d1fd18a2ef5db25e14575fb0ab2eb9d44","abstract_canon_sha256":"c2e5fd0a545a04aa346b62b78350435f6c54461719eb7b735b411754cb3f7efd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:41.628681Z","signature_b64":"Im6Bz7MkCMRpddqC+a45oad66nhAOi6z2Y4rL0PmkaWVl4rlACbV6a8XR7XEZp8TsKH4jZKi/ug2JxThwrmVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"236d1254f98a79a76b26ea2f726ec9cd46ad4484b6c87573c78736655f250739","last_reissued_at":"2026-07-05T11:35:41.628198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:41.628198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIDI-VALLE: Improving Expressive Piano Performance Synthesis Through Neural Codec Language Modelling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"George Fazekas, Geraint Wiggins, Jingjing Tang, Junichi Yamagishi, Xin Wang, Zhe Zhang","submitted_at":"2025-07-11T12:28:20Z","abstract_excerpt":"Generating expressive audio performances from music scores requires models to capture both instrument acoustics and human interpretation. Traditional music performance synthesis pipelines follow a two-stage approach, first generating expressive performance MIDI from a score, then synthesising the MIDI into audio. However, the synthesis models often struggle to generalise across diverse MIDI sources, musical styles, and recording environments. To address these challenges, we propose MIDI-VALLE, a neural codec language model adapted from the VALLE framework, which was originally designed for zer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08530","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/2507.08530/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":"2507.08530","created_at":"2026-07-05T11:35:41.628254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08530v1","created_at":"2026-07-05T11:35:41.628254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08530","created_at":"2026-07-05T11:35:41.628254+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENWREVHZRJ42","created_at":"2026-07-05T11:35:41.628254+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENWREVHZRJ42O2ZG","created_at":"2026-07-05T11:35:41.628254+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENWREVHZ","created_at":"2026-07-05T11:35:41.628254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10281","citing_title":"Drum Synthesis from Expressive Drum Grids via Neural Audio Codecs","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV","json":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV.json","graph_json":"https://pith.science/api/pith-number/ENWREVHZRJ42O2ZG5IXXE3WJZV/graph.json","events_json":"https://pith.science/api/pith-number/ENWREVHZRJ42O2ZG5IXXE3WJZV/events.json","paper":"https://pith.science/paper/ENWREVHZ"},"agent_actions":{"view_html":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV","download_json":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV.json","view_paper":"https://pith.science/paper/ENWREVHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08530&json=true","fetch_graph":"https://pith.science/api/pith-number/ENWREVHZRJ42O2ZG5IXXE3WJZV/graph.json","fetch_events":"https://pith.science/api/pith-number/ENWREVHZRJ42O2ZG5IXXE3WJZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV/action/storage_attestation","attest_author":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV/action/author_attestation","sign_citation":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV/action/citation_signature","submit_replication":"https://pith.science/pith/ENWREVHZRJ42O2ZG5IXXE3WJZV/action/replication_record"}},"created_at":"2026-07-05T11:35:41.628254+00:00","updated_at":"2026-07-05T11:35:41.628254+00:00"}