{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WCADU5Q4CEWCUOGEWDUXOPMMUX","short_pith_number":"pith:WCADU5Q4","schema_version":"1.0","canonical_sha256":"b0803a761c112c2a38c4b0e9773d8ca5f602dbc6783ba2db0f7d4247df7b131a","source":{"kind":"arxiv","id":"2208.04756","version":2},"attestation_state":"computed","paper":{"title":"DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Da-Yi Wu, Fu-Rong Yang, Oscar Friedman, Scott Bruzenak, Warren Jackson, Wen-Yi Hsiao, Yi-Hsuan Yang, Yi-Wen Liu","submitted_at":"2022-08-09T13:06:08Z","abstract_excerpt":"A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal Processing (DDSP), we propose a new vocoder named SawSing for singing voices. SawSing synthesizes the harmonic part of singing voices by filtering a sawtooth source signal with a linear time-variant finite impulse response filter whose coefficients are estimated from the input mel-spectrogram by a neural network. As this approach enforces phase continuity, SawSing can generate singing voices without the phase-discontinu"},"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":"2208.04756","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-08-09T13:06:08Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"291dd286f55d604951c3b52123aa3cfabea3d9588ad23e2537627dc601641b10","abstract_canon_sha256":"63fc599e57cca52d916130a3bb4c2a68f9cf3c10f90241d4c019a986329141a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:54.413495Z","signature_b64":"BMPJjuGKaXGPHuP7LZQUEhpYtjk2jcQhJb1N4WKN1jey7QQNcjXzC1Kj3x2hrgXd+ZCge6YMI6UclRWs5zxQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0803a761c112c2a38c4b0e9773d8ca5f602dbc6783ba2db0f7d4247df7b131a","last_reissued_at":"2026-07-05T04:49:54.413143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:54.413143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Da-Yi Wu, Fu-Rong Yang, Oscar Friedman, Scott Bruzenak, Warren Jackson, Wen-Yi Hsiao, Yi-Hsuan Yang, Yi-Wen Liu","submitted_at":"2022-08-09T13:06:08Z","abstract_excerpt":"A vocoder is a conditional audio generation model that converts acoustic features such as mel-spectrograms into waveforms. Taking inspiration from Differentiable Digital Signal Processing (DDSP), we propose a new vocoder named SawSing for singing voices. SawSing synthesizes the harmonic part of singing voices by filtering a sawtooth source signal with a linear time-variant finite impulse response filter whose coefficients are estimated from the input mel-spectrogram by a neural network. As this approach enforces phase continuity, SawSing can generate singing voices without the phase-discontinu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04756","kind":"arxiv","version":2},"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/2208.04756/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":"2208.04756","created_at":"2026-07-05T04:49:54.413198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.04756v2","created_at":"2026-07-05T04:49:54.413198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04756","created_at":"2026-07-05T04:49:54.413198+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCADU5Q4CEWC","created_at":"2026-07-05T04:49:54.413198+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCADU5Q4CEWCUOGE","created_at":"2026-07-05T04:49:54.413198+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCADU5Q4","created_at":"2026-07-05T04:49:54.413198+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/WCADU5Q4CEWCUOGEWDUXOPMMUX","json":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX.json","graph_json":"https://pith.science/api/pith-number/WCADU5Q4CEWCUOGEWDUXOPMMUX/graph.json","events_json":"https://pith.science/api/pith-number/WCADU5Q4CEWCUOGEWDUXOPMMUX/events.json","paper":"https://pith.science/paper/WCADU5Q4"},"agent_actions":{"view_html":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX","download_json":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX.json","view_paper":"https://pith.science/paper/WCADU5Q4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.04756&json=true","fetch_graph":"https://pith.science/api/pith-number/WCADU5Q4CEWCUOGEWDUXOPMMUX/graph.json","fetch_events":"https://pith.science/api/pith-number/WCADU5Q4CEWCUOGEWDUXOPMMUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX/action/storage_attestation","attest_author":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX/action/author_attestation","sign_citation":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX/action/citation_signature","submit_replication":"https://pith.science/pith/WCADU5Q4CEWCUOGEWDUXOPMMUX/action/replication_record"}},"created_at":"2026-07-05T04:49:54.413198+00:00","updated_at":"2026-07-05T04:49:54.413198+00:00"}