{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4USBAF2JBGASUGGSOX6F4LK2QL","short_pith_number":"pith:4USBAF2J","schema_version":"1.0","canonical_sha256":"e52410174909812a18d275fc5e2d5a82cfad7a1eacc4324ca35475b2aba39245","source":{"kind":"arxiv","id":"2502.12759","version":1},"attestation_state":"computed","paper":{"title":"High-Fidelity Music Vocoder using Neural Audio Codecs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Florian Gr\\\"otschla, Luca A. Lanzend\\\"orfer, Michael Ungersb\\\"ock, Roger Wattenhofer","submitted_at":"2025-02-18T11:25:46Z","abstract_excerpt":"While neural vocoders have made significant progress in high-fidelity speech synthesis, their application on polyphonic music has remained underexplored. In this work, we propose DisCoder, a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audio codec to reconstruct high-fidelity 44.1 kHz audio from mel spectrograms. Our approach first transforms the mel spectrogram into a lower-dimensional representation aligned with the Descript Audio Codec (DAC) latent space before reconstructing it to an audio signal using a fine-tuned DAC decoder. Di"},"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":"2502.12759","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-18T11:25:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"df5b744741db9b0fdf99d72e261e766a4f5d835350d80a565fefa8cd9449cec7","abstract_canon_sha256":"1c683221d29d2b6c5fe21fc817c81641390752886f5cf34621af861a435c9f5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:23.841021Z","signature_b64":"ZKNx1E2Rc4I/DbBJFihbhX6flJQHuRxTOdG32xK04O8bUebi8b/3RFOTYJbLIQYQFJCeDCxCpnzuOfOBvMdMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e52410174909812a18d275fc5e2d5a82cfad7a1eacc4324ca35475b2aba39245","last_reissued_at":"2026-07-05T10:16:23.840569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:23.840569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Fidelity Music Vocoder using Neural Audio Codecs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Florian Gr\\\"otschla, Luca A. Lanzend\\\"orfer, Michael Ungersb\\\"ock, Roger Wattenhofer","submitted_at":"2025-02-18T11:25:46Z","abstract_excerpt":"While neural vocoders have made significant progress in high-fidelity speech synthesis, their application on polyphonic music has remained underexplored. In this work, we propose DisCoder, a neural vocoder that leverages a generative adversarial encoder-decoder architecture informed by a neural audio codec to reconstruct high-fidelity 44.1 kHz audio from mel spectrograms. Our approach first transforms the mel spectrogram into a lower-dimensional representation aligned with the Descript Audio Codec (DAC) latent space before reconstructing it to an audio signal using a fine-tuned DAC decoder. Di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12759","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/2502.12759/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":"2502.12759","created_at":"2026-07-05T10:16:23.840624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12759v1","created_at":"2026-07-05T10:16:23.840624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12759","created_at":"2026-07-05T10:16:23.840624+00:00"},{"alias_kind":"pith_short_12","alias_value":"4USBAF2JBGAS","created_at":"2026-07-05T10:16:23.840624+00:00"},{"alias_kind":"pith_short_16","alias_value":"4USBAF2JBGASUGGS","created_at":"2026-07-05T10:16:23.840624+00:00"},{"alias_kind":"pith_short_8","alias_value":"4USBAF2J","created_at":"2026-07-05T10:16:23.840624+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/4USBAF2JBGASUGGSOX6F4LK2QL","json":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL.json","graph_json":"https://pith.science/api/pith-number/4USBAF2JBGASUGGSOX6F4LK2QL/graph.json","events_json":"https://pith.science/api/pith-number/4USBAF2JBGASUGGSOX6F4LK2QL/events.json","paper":"https://pith.science/paper/4USBAF2J"},"agent_actions":{"view_html":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL","download_json":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL.json","view_paper":"https://pith.science/paper/4USBAF2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12759&json=true","fetch_graph":"https://pith.science/api/pith-number/4USBAF2JBGASUGGSOX6F4LK2QL/graph.json","fetch_events":"https://pith.science/api/pith-number/4USBAF2JBGASUGGSOX6F4LK2QL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL/action/storage_attestation","attest_author":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL/action/author_attestation","sign_citation":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL/action/citation_signature","submit_replication":"https://pith.science/pith/4USBAF2JBGASUGGSOX6F4LK2QL/action/replication_record"}},"created_at":"2026-07-05T10:16:23.840624+00:00","updated_at":"2026-07-05T10:16:23.840624+00:00"}