{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PZV5KWNDJ4R34LPJERVPA7R2PR","short_pith_number":"pith:PZV5KWND","schema_version":"1.0","canonical_sha256":"7e6bd559a34f23be2de9246af07e3a7c679a0d7a2efc8ece935c9fbafdc5b717","source":{"kind":"arxiv","id":"2407.15641","version":1},"attestation_state":"computed","paper":{"title":"Generating Sample-Based Musical Instruments Using Neural Audio Codec Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Frederik Blang, Johannes Imort, Ninon Devis, Shahan Nercessian","submitted_at":"2024-07-22T13:59:58Z","abstract_excerpt":"In this paper, we propose and investigate the use of neural audio codec language models for the automatic generation of sample-based musical instruments based on text or reference audio prompts. Our approach extends a generative audio framework to condition on pitch across an 88-key spectrum, velocity, and a combined text/audio embedding. We identify maintaining timbral consistency within the generated instruments as a major challenge. To tackle this issue, we introduce three distinct conditioning schemes. We analyze our methods through objective metrics and human listening tests, demonstratin"},"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":"2407.15641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-07-22T13:59:58Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"ebf92609993c22a6384d009d994477e87150ba7a1c60b6496212212ef976ac6b","abstract_canon_sha256":"3540e743b593aa4ed05e84103b7f52029c404f557cbc0ba3a474a0254c6caf56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:59.195347Z","signature_b64":"ungmMjwr7leh0FQoKAswXTrUczPYsBXnVj87nKQWlePi33zuJ3cWYmL4Nfx9m4cYuP3Y/VzmR/bnoT1qxleBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e6bd559a34f23be2de9246af07e3a7c679a0d7a2efc8ece935c9fbafdc5b717","last_reissued_at":"2026-07-05T08:46:59.194779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:59.194779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Sample-Based Musical Instruments Using Neural Audio Codec Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Frederik Blang, Johannes Imort, Ninon Devis, Shahan Nercessian","submitted_at":"2024-07-22T13:59:58Z","abstract_excerpt":"In this paper, we propose and investigate the use of neural audio codec language models for the automatic generation of sample-based musical instruments based on text or reference audio prompts. Our approach extends a generative audio framework to condition on pitch across an 88-key spectrum, velocity, and a combined text/audio embedding. We identify maintaining timbral consistency within the generated instruments as a major challenge. To tackle this issue, we introduce three distinct conditioning schemes. We analyze our methods through objective metrics and human listening tests, demonstratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15641","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/2407.15641/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":"2407.15641","created_at":"2026-07-05T08:46:59.194839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15641v1","created_at":"2026-07-05T08:46:59.194839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15641","created_at":"2026-07-05T08:46:59.194839+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZV5KWNDJ4R3","created_at":"2026-07-05T08:46:59.194839+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZV5KWNDJ4R34LPJ","created_at":"2026-07-05T08:46:59.194839+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZV5KWND","created_at":"2026-07-05T08:46:59.194839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08939","citing_title":"TokenSynth: A Token-based Neural Synthesizer for Instrument Cloning and Text-to-Instrument","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR","json":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR.json","graph_json":"https://pith.science/api/pith-number/PZV5KWNDJ4R34LPJERVPA7R2PR/graph.json","events_json":"https://pith.science/api/pith-number/PZV5KWNDJ4R34LPJERVPA7R2PR/events.json","paper":"https://pith.science/paper/PZV5KWND"},"agent_actions":{"view_html":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR","download_json":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR.json","view_paper":"https://pith.science/paper/PZV5KWND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15641&json=true","fetch_graph":"https://pith.science/api/pith-number/PZV5KWNDJ4R34LPJERVPA7R2PR/graph.json","fetch_events":"https://pith.science/api/pith-number/PZV5KWNDJ4R34LPJERVPA7R2PR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR/action/storage_attestation","attest_author":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR/action/author_attestation","sign_citation":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR/action/citation_signature","submit_replication":"https://pith.science/pith/PZV5KWNDJ4R34LPJERVPA7R2PR/action/replication_record"}},"created_at":"2026-07-05T08:46:59.194839+00:00","updated_at":"2026-07-05T08:46:59.194839+00:00"}