{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QNPXZT34E6BNPVQMDYVBYS6UPU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"195fb4d0c1aa74c3518951be24cfd00c817504214c29d2b6884660bd74869d31","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T16:05:48Z","title_canon_sha256":"e2d1e1cbab817a855fea4c833483dc56ec62b2f87c829072d391be4d7e69038d"},"schema_version":"1.0","source":{"id":"2203.02395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.02395","created_at":"2026-07-05T04:02:04Z"},{"alias_kind":"arxiv_version","alias_value":"2203.02395v1","created_at":"2026-07-05T04:02:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02395","created_at":"2026-07-05T04:02:04Z"},{"alias_kind":"pith_short_12","alias_value":"QNPXZT34E6BN","created_at":"2026-07-05T04:02:04Z"},{"alias_kind":"pith_short_16","alias_value":"QNPXZT34E6BNPVQM","created_at":"2026-07-05T04:02:04Z"},{"alias_kind":"pith_short_8","alias_value":"QNPXZT34","created_at":"2026-07-05T04:02:04Z"}],"graph_snapshots":[{"event_id":"sha256:876051f38b716eca345dc5421bed5a22131d18b0e825c4a679f5d562d761e754","target":"graph","created_at":"2026-07-05T04:02:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.02395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent text-to-speech synthesis and voice conversion systems, a mel-spectrogram is commonly applied as an intermediate representation, and the necessity for a mel-spectrogram vocoder is increasing. A mel-spectrogram vocoder must solve three inverse problems: recovery of the original-scale magnitude spectrogram, phase reconstruction, and frequency-to-time conversion. A typical convolutional mel-spectrogram vocoder solves these problems jointly and implicitly using a convolutional neural network, including temporal upsampling layers, when directly calculating a raw waveform. Such an approach ","authors_text":"Hirokazu Kameoka, Kou Tanaka, Shogo Seki, Takuhiro Kaneko","cross_cats":["cs.LG","eess.AS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T16:05:48Z","title":"iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02395","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7cff820d7e611126088f1fafd7230968e010331af545c4719c470bf2fa956317","target":"record","created_at":"2026-07-05T04:02:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"195fb4d0c1aa74c3518951be24cfd00c817504214c29d2b6884660bd74869d31","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T16:05:48Z","title_canon_sha256":"e2d1e1cbab817a855fea4c833483dc56ec62b2f87c829072d391be4d7e69038d"},"schema_version":"1.0","source":{"id":"2203.02395","kind":"arxiv","version":1}},"canonical_sha256":"835f7ccf7c2782d7d60c1e2a1c4bd47d3a7ba78b908159ce7f0e412c7b46d3cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"835f7ccf7c2782d7d60c1e2a1c4bd47d3a7ba78b908159ce7f0e412c7b46d3cd","first_computed_at":"2026-07-05T04:02:04.250235Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:02:04.250235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ym0rB49SgksWxdg8cdMYdxBQWFL3QjRLxnDiTD5yGMDs9fxIjCWfymr/ZcsRHsAPTm/y+/fDn/6xAwOxeTdEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:02:04.250632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.02395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cff820d7e611126088f1fafd7230968e010331af545c4719c470bf2fa956317","sha256:876051f38b716eca345dc5421bed5a22131d18b0e825c4a679f5d562d761e754"],"state_sha256":"8b67abd9e269bc02852f985c696ec615ae5e5f2ca9401fbed9885390558468f7"}