{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UWQRB3WX67R2XBCBVWBD3JFYFX","short_pith_number":"pith:UWQRB3WX","schema_version":"1.0","canonical_sha256":"a5a110eed7f7e3ab8441ad823da4b82dcdf49330ec8cbed122fcb3728cf6f471","source":{"kind":"arxiv","id":"2211.08715","version":1},"attestation_state":"computed","paper":{"title":"Conditional variational autoencoder to improve neural audio synthesis for polyphonic music sound","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"DaeHo Lee, Inseon Jang, Minhan Kim, Seokjin Lee, Seunghyeon Shin, Wootaek Lim","submitted_at":"2022-11-16T07:11:56Z","abstract_excerpt":"Deep generative models for audio synthesis have recently been significantly improved. However, the task of modeling raw-waveforms remains a difficult problem, especially for audio waveforms and music signals. Recently, the realtime audio variational autoencoder (RAVE) method was developed for high-quality audio waveform synthesis. The RAVE method is based on the variational autoencoder and utilizes the two-stage training strategy. Unfortunately, the RAVE model is limited in reproducing wide-pitch polyphonic music sound. Therefore, to enhance the reconstruction performance, we adopt the pitch a"},"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":"2211.08715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-16T07:11:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"535deea14a8c4e1b280147b22e8971eaec3a4b7bd8831b9d17707a85e38b5f0f","abstract_canon_sha256":"9b391f59045bb8cabb323ee6131a7387c012e355dd2d28750dc374c8e2128228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:43.117289Z","signature_b64":"s5HtNFDt5ddqdccHgL90ZRpeUtoTI2Hs7QlwnVV3clgdxhwG9+43yWrsRijk3EtZD6mu5ddQZwnm4V+SGHF9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5a110eed7f7e3ab8441ad823da4b82dcdf49330ec8cbed122fcb3728cf6f471","last_reissued_at":"2026-07-05T05:16:43.116838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:43.116838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional variational autoencoder to improve neural audio synthesis for polyphonic music sound","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"DaeHo Lee, Inseon Jang, Minhan Kim, Seokjin Lee, Seunghyeon Shin, Wootaek Lim","submitted_at":"2022-11-16T07:11:56Z","abstract_excerpt":"Deep generative models for audio synthesis have recently been significantly improved. However, the task of modeling raw-waveforms remains a difficult problem, especially for audio waveforms and music signals. Recently, the realtime audio variational autoencoder (RAVE) method was developed for high-quality audio waveform synthesis. The RAVE method is based on the variational autoencoder and utilizes the two-stage training strategy. Unfortunately, the RAVE model is limited in reproducing wide-pitch polyphonic music sound. Therefore, to enhance the reconstruction performance, we adopt the pitch a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08715","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/2211.08715/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":"2211.08715","created_at":"2026-07-05T05:16:43.116898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08715v1","created_at":"2026-07-05T05:16:43.116898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08715","created_at":"2026-07-05T05:16:43.116898+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWQRB3WX67R2","created_at":"2026-07-05T05:16:43.116898+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWQRB3WX67R2XBCB","created_at":"2026-07-05T05:16:43.116898+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWQRB3WX","created_at":"2026-07-05T05:16:43.116898+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/UWQRB3WX67R2XBCBVWBD3JFYFX","json":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX.json","graph_json":"https://pith.science/api/pith-number/UWQRB3WX67R2XBCBVWBD3JFYFX/graph.json","events_json":"https://pith.science/api/pith-number/UWQRB3WX67R2XBCBVWBD3JFYFX/events.json","paper":"https://pith.science/paper/UWQRB3WX"},"agent_actions":{"view_html":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX","download_json":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX.json","view_paper":"https://pith.science/paper/UWQRB3WX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08715&json=true","fetch_graph":"https://pith.science/api/pith-number/UWQRB3WX67R2XBCBVWBD3JFYFX/graph.json","fetch_events":"https://pith.science/api/pith-number/UWQRB3WX67R2XBCBVWBD3JFYFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX/action/storage_attestation","attest_author":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX/action/author_attestation","sign_citation":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX/action/citation_signature","submit_replication":"https://pith.science/pith/UWQRB3WX67R2XBCBVWBD3JFYFX/action/replication_record"}},"created_at":"2026-07-05T05:16:43.116898+00:00","updated_at":"2026-07-05T05:16:43.116898+00:00"}