{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QNPXZT34E6BNPVQMDYVBYS6UPU","short_pith_number":"pith:QNPXZT34","schema_version":"1.0","canonical_sha256":"835f7ccf7c2782d7d60c1e2a1c4bd47d3a7ba78b908159ce7f0e412c7b46d3cd","source":{"kind":"arxiv","id":"2203.02395","version":1},"attestation_state":"computed","paper":{"title":"iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hirokazu Kameoka, Kou Tanaka, Shogo Seki, Takuhiro Kaneko","submitted_at":"2022-03-04T16:05:48Z","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 "},"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":"2203.02395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-04T16:05:48Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"e2d1e1cbab817a855fea4c833483dc56ec62b2f87c829072d391be4d7e69038d","abstract_canon_sha256":"195fb4d0c1aa74c3518951be24cfd00c817504214c29d2b6884660bd74869d31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:02:04.250632Z","signature_b64":"Ym0rB49SgksWxdg8cdMYdxBQWFL3QjRLxnDiTD5yGMDs9fxIjCWfymr/ZcsRHsAPTm/y+/fDn/6xAwOxeTdEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"835f7ccf7c2782d7d60c1e2a1c4bd47d3a7ba78b908159ce7f0e412c7b46d3cd","last_reissued_at":"2026-07-05T04:02:04.250235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:02:04.250235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Hirokazu Kameoka, Kou Tanaka, Shogo Seki, Takuhiro Kaneko","submitted_at":"2022-03-04T16:05:48Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02395","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/2203.02395/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":"2203.02395","created_at":"2026-07-05T04:02:04.250295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02395v1","created_at":"2026-07-05T04:02:04.250295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02395","created_at":"2026-07-05T04:02:04.250295+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNPXZT34E6BN","created_at":"2026-07-05T04:02:04.250295+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNPXZT34E6BNPVQM","created_at":"2026-07-05T04:02:04.250295+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNPXZT34","created_at":"2026-07-05T04:02:04.250295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20606","citing_title":"Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU","json":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU.json","graph_json":"https://pith.science/api/pith-number/QNPXZT34E6BNPVQMDYVBYS6UPU/graph.json","events_json":"https://pith.science/api/pith-number/QNPXZT34E6BNPVQMDYVBYS6UPU/events.json","paper":"https://pith.science/paper/QNPXZT34"},"agent_actions":{"view_html":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU","download_json":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU.json","view_paper":"https://pith.science/paper/QNPXZT34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02395&json=true","fetch_graph":"https://pith.science/api/pith-number/QNPXZT34E6BNPVQMDYVBYS6UPU/graph.json","fetch_events":"https://pith.science/api/pith-number/QNPXZT34E6BNPVQMDYVBYS6UPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU/action/storage_attestation","attest_author":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU/action/author_attestation","sign_citation":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU/action/citation_signature","submit_replication":"https://pith.science/pith/QNPXZT34E6BNPVQMDYVBYS6UPU/action/replication_record"}},"created_at":"2026-07-05T04:02:04.250295+00:00","updated_at":"2026-07-05T04:02:04.250295+00:00"}