{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4IGN56CTYNPWGNC3X356VJITW","short_pith_number":"pith:T4IGN56C","schema_version":"1.0","canonical_sha256":"9f1066f7c29e1afb19a2ddf7df55289d8b609474a5fbcf9506f65935b04c24c7","source":{"kind":"arxiv","id":"2403.10493","version":4},"attestation_state":"computed","paper":{"title":"MusicHiFi: Fast High-Fidelity Stereo Vocoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Ge Zhu, Juan-Pablo Caceres, Nicholas J. Bryan, Zhiyao Duan","submitted_at":"2024-03-15T17:27:42Z","abstract_excerpt":"Diffusion-based audio and music generation models commonly perform generation by constructing an image representation of audio (e.g., a mel-spectrogram) and then convert it to audio using a phase reconstruction model or vocoder. Typical vocoders, however, produce monophonic audio at lower resolutions (e.g., 16-24 kHz), which limits their usefulness. We propose MusicHiFi -- an efficient high-fidelity stereophonic vocoder. Our method employs a cascade of three generative adversarial networks (GANs) that convert low-resolution mel-spectrograms to audio, upsamples to high-resolution audio via band"},"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":"2403.10493","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-15T17:27:42Z","cross_cats_sorted":["eess.AS","eess.SP"],"title_canon_sha256":"0ddd576fe948d6898b05a0a75e062c6a69a742b19fc679698a287f684702c903","abstract_canon_sha256":"693e44662d8101ecd26cd74b1aead657c88736bc5d9e1ab5c928ca841906a9c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:13.613827Z","signature_b64":"MZOotpoZCGwceR9flJuNh8+vaK69Z7P/cv7i+KbaBqKJ3TFOHZTF5OBPPKQ8wimoAShezCTeHK/MtM8Fn7WnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f1066f7c29e1afb19a2ddf7df55289d8b609474a5fbcf9506f65935b04c24c7","last_reissued_at":"2026-07-05T09:16:13.613294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:13.613294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MusicHiFi: Fast High-Fidelity Stereo Vocoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Ge Zhu, Juan-Pablo Caceres, Nicholas J. Bryan, Zhiyao Duan","submitted_at":"2024-03-15T17:27:42Z","abstract_excerpt":"Diffusion-based audio and music generation models commonly perform generation by constructing an image representation of audio (e.g., a mel-spectrogram) and then convert it to audio using a phase reconstruction model or vocoder. Typical vocoders, however, produce monophonic audio at lower resolutions (e.g., 16-24 kHz), which limits their usefulness. We propose MusicHiFi -- an efficient high-fidelity stereophonic vocoder. Our method employs a cascade of three generative adversarial networks (GANs) that convert low-resolution mel-spectrograms to audio, upsamples to high-resolution audio via band"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10493","kind":"arxiv","version":4},"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/2403.10493/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":"2403.10493","created_at":"2026-07-05T09:16:13.613379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10493v4","created_at":"2026-07-05T09:16:13.613379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10493","created_at":"2026-07-05T09:16:13.613379+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4IGN56CTYNP","created_at":"2026-07-05T09:16:13.613379+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4IGN56CTYNPWGNC","created_at":"2026-07-05T09:16:13.613379+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4IGN56C","created_at":"2026-07-05T09:16:13.613379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07897","citing_title":"Bridge-SR: Schr\\\"odinger Bridge for Efficient SR","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW","json":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW.json","graph_json":"https://pith.science/api/pith-number/T4IGN56CTYNPWGNC3X356VJITW/graph.json","events_json":"https://pith.science/api/pith-number/T4IGN56CTYNPWGNC3X356VJITW/events.json","paper":"https://pith.science/paper/T4IGN56C"},"agent_actions":{"view_html":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW","download_json":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW.json","view_paper":"https://pith.science/paper/T4IGN56C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10493&json=true","fetch_graph":"https://pith.science/api/pith-number/T4IGN56CTYNPWGNC3X356VJITW/graph.json","fetch_events":"https://pith.science/api/pith-number/T4IGN56CTYNPWGNC3X356VJITW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW/action/storage_attestation","attest_author":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW/action/author_attestation","sign_citation":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW/action/citation_signature","submit_replication":"https://pith.science/pith/T4IGN56CTYNPWGNC3X356VJITW/action/replication_record"}},"created_at":"2026-07-05T09:16:13.613379+00:00","updated_at":"2026-07-05T09:16:13.613379+00:00"}