{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KDKER2Z5WNIYIIMESCA3AT35GV","short_pith_number":"pith:KDKER2Z5","schema_version":"1.0","canonical_sha256":"50d448eb3db3518421849081b04f7d354ad8bd85471ae6b8fe758a45cc6397b3","source":{"kind":"arxiv","id":"2406.08196","version":1},"attestation_state":"computed","paper":{"title":"FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Danming Xie, Hai Li, Junhui Liu, Lei Xie, Ying Yan, Yuanjun Lv","submitted_at":"2024-06-12T13:29:36Z","abstract_excerpt":"Vocoders reconstruct speech waveforms from acoustic features and play a pivotal role in modern TTS systems. Frequent-domain GAN vocoders like Vocos and APNet2 have recently seen rapid advancements, outperforming time-domain models in inference speed while achieving comparable audio quality. However, these frequency-domain vocoders suffer from large parameter sizes, thus introducing extra memory burden. Inspired by PriorGrad and SpecGrad, we employ pseudo-inverse to estimate the amplitude spectrum as the initialization roughly. This simple initialization significantly mitigates the parameter de"},"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":"2406.08196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T13:29:36Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"341ca2db93c3a7eaa82765248d5ed75e1c8b45c12f9a2f426bcd8ffa2c893e6e","abstract_canon_sha256":"39f4942a97adaa568316629c8031cbdb594301f8e7a0644a476430e495a2a62f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:56.521897Z","signature_b64":"p43cn1tKS83prNZeMLYywD3Mk7DMTAWtrffYMXTdIm3/MlB2HR+A1r9YN++tTn+4GzSMRgA6jvZhSiy0kcBwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d448eb3db3518421849081b04f7d354ad8bd85471ae6b8fe758a45cc6397b3","last_reissued_at":"2026-07-05T08:30:56.521453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:56.521453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeV: Free Lunch For Vocoders Through Pseudo Inversed Mel Filter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Danming Xie, Hai Li, Junhui Liu, Lei Xie, Ying Yan, Yuanjun Lv","submitted_at":"2024-06-12T13:29:36Z","abstract_excerpt":"Vocoders reconstruct speech waveforms from acoustic features and play a pivotal role in modern TTS systems. Frequent-domain GAN vocoders like Vocos and APNet2 have recently seen rapid advancements, outperforming time-domain models in inference speed while achieving comparable audio quality. However, these frequency-domain vocoders suffer from large parameter sizes, thus introducing extra memory burden. Inspired by PriorGrad and SpecGrad, we employ pseudo-inverse to estimate the amplitude spectrum as the initialization roughly. This simple initialization significantly mitigates the parameter de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08196","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/2406.08196/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":"2406.08196","created_at":"2026-07-05T08:30:56.521512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08196v1","created_at":"2026-07-05T08:30:56.521512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08196","created_at":"2026-07-05T08:30:56.521512+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDKER2Z5WNIY","created_at":"2026-07-05T08:30:56.521512+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDKER2Z5WNIYIIME","created_at":"2026-07-05T08:30:56.521512+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDKER2Z5","created_at":"2026-07-05T08:30:56.521512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02703","citing_title":"Developing multilingual speech synthesis system for Ojibwe, Mi'kmaq, and Maliseet","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV","json":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV.json","graph_json":"https://pith.science/api/pith-number/KDKER2Z5WNIYIIMESCA3AT35GV/graph.json","events_json":"https://pith.science/api/pith-number/KDKER2Z5WNIYIIMESCA3AT35GV/events.json","paper":"https://pith.science/paper/KDKER2Z5"},"agent_actions":{"view_html":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV","download_json":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV.json","view_paper":"https://pith.science/paper/KDKER2Z5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08196&json=true","fetch_graph":"https://pith.science/api/pith-number/KDKER2Z5WNIYIIMESCA3AT35GV/graph.json","fetch_events":"https://pith.science/api/pith-number/KDKER2Z5WNIYIIMESCA3AT35GV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV/action/storage_attestation","attest_author":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV/action/author_attestation","sign_citation":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV/action/citation_signature","submit_replication":"https://pith.science/pith/KDKER2Z5WNIYIIMESCA3AT35GV/action/replication_record"}},"created_at":"2026-07-05T08:30:56.521512+00:00","updated_at":"2026-07-05T08:30:56.521512+00:00"}