{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:35NG4XLE532U6AXYPGAWTJ5OGR","short_pith_number":"pith:35NG4XLE","schema_version":"1.0","canonical_sha256":"df5a6e5d64eef54f02f8798169a7ae344f0138ce6e39b73e4b60b410ab62efbb","source":{"kind":"arxiv","id":"2204.10561","version":1},"attestation_state":"computed","paper":{"title":"Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Detai Xin, Hiroshi Saruwatari, Hisashi Kawai, Shinnosuke Takamichi, Takuma Okamoto","submitted_at":"2022-04-22T08:18:08Z","abstract_excerpt":"This paper presents a speaking-rate-controllable HiFi-GAN neural vocoder. Original HiFi-GAN is a high-fidelity, computationally efficient, and tiny-footprint neural vocoder. We attempt to incorporate a speaking rate control function into HiFi-GAN for improving the accessibility of synthetic speech. The proposed method inserts a differentiable interpolation layer into the HiFi-GAN architecture. A signal resampling method and an image scaling method are implemented in the proposed method to warp the mel-spectrograms or hidden features of the neural vocoder. We also design and open-source a Japan"},"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":"2204.10561","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-22T08:18:08Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d45c825b0f00ce75e6425a8685e5cffb58202df62c15e756526980b124aaf5bd","abstract_canon_sha256":"be98a3883e08525c5ee2fe0b9232508c21afb84c663931d1d8ba5d25adbbba30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:58.444360Z","signature_b64":"78OqdzGkpAVR9H9SsIL8FamqXds+0dmMAZ15rNigCoaQ0cgyekk/4U5Pax+WKNDgxsAxLt+S2fk+isZnT5pvCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df5a6e5d64eef54f02f8798169a7ae344f0138ce6e39b73e4b60b410ab62efbb","last_reissued_at":"2026-07-05T04:16:58.443893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:58.443893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Detai Xin, Hiroshi Saruwatari, Hisashi Kawai, Shinnosuke Takamichi, Takuma Okamoto","submitted_at":"2022-04-22T08:18:08Z","abstract_excerpt":"This paper presents a speaking-rate-controllable HiFi-GAN neural vocoder. Original HiFi-GAN is a high-fidelity, computationally efficient, and tiny-footprint neural vocoder. We attempt to incorporate a speaking rate control function into HiFi-GAN for improving the accessibility of synthetic speech. The proposed method inserts a differentiable interpolation layer into the HiFi-GAN architecture. A signal resampling method and an image scaling method are implemented in the proposed method to warp the mel-spectrograms or hidden features of the neural vocoder. We also design and open-source a Japan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.10561","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/2204.10561/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":"2204.10561","created_at":"2026-07-05T04:16:58.443943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.10561v1","created_at":"2026-07-05T04:16:58.443943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.10561","created_at":"2026-07-05T04:16:58.443943+00:00"},{"alias_kind":"pith_short_12","alias_value":"35NG4XLE532U","created_at":"2026-07-05T04:16:58.443943+00:00"},{"alias_kind":"pith_short_16","alias_value":"35NG4XLE532U6AXY","created_at":"2026-07-05T04:16:58.443943+00:00"},{"alias_kind":"pith_short_8","alias_value":"35NG4XLE","created_at":"2026-07-05T04:16:58.443943+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/35NG4XLE532U6AXYPGAWTJ5OGR","json":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR.json","graph_json":"https://pith.science/api/pith-number/35NG4XLE532U6AXYPGAWTJ5OGR/graph.json","events_json":"https://pith.science/api/pith-number/35NG4XLE532U6AXYPGAWTJ5OGR/events.json","paper":"https://pith.science/paper/35NG4XLE"},"agent_actions":{"view_html":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR","download_json":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR.json","view_paper":"https://pith.science/paper/35NG4XLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.10561&json=true","fetch_graph":"https://pith.science/api/pith-number/35NG4XLE532U6AXYPGAWTJ5OGR/graph.json","fetch_events":"https://pith.science/api/pith-number/35NG4XLE532U6AXYPGAWTJ5OGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR/action/storage_attestation","attest_author":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR/action/author_attestation","sign_citation":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR/action/citation_signature","submit_replication":"https://pith.science/pith/35NG4XLE532U6AXYPGAWTJ5OGR/action/replication_record"}},"created_at":"2026-07-05T04:16:58.443943+00:00","updated_at":"2026-07-05T04:16:58.443943+00:00"}