{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7RPNXV53HZBXPRTZB6L5OD33PI","short_pith_number":"pith:7RPNXV53","schema_version":"1.0","canonical_sha256":"fc5edbd7bb3e4377c6790f97d70f7b7a01cb78eb0a3facfb595840c482fb1950","source":{"kind":"arxiv","id":"2106.07889","version":1},"attestation_state":"computed","paper":{"title":"UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bongwan Kim, Dan Lim, Jaesam Yoon, Juntae Kim, Won Jang","submitted_at":"2021-06-15T05:35:34Z","abstract_excerpt":"Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models employing full-band mel-spectrograms, an over-smoothing problem occurs as part of which non-sharp spectrograms are generated. To address this problem, we propose UnivNet, a neural vocoder that synthesizes high-fidelity waveforms in real time. Inspired by works in the field of voice activity detection, we added a multi-resolution spectrogram discriminator that empl"},"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":"2106.07889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-15T05:35:34Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6eae9cbfe02b19491648378ff2b061c961f0e6c5b244c934a87156528ec33224","abstract_canon_sha256":"a26969bbdd6dbf8522b6769961fe466ab434b79df5dcd2675c69b5f47804de58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:35.038489Z","signature_b64":"qZZTGsU5B5CUx5W/UupIdXkmqlInJGdxNfRnooJKphegbkvutfqFBoW+wg8iL2k+13hQcoDxZJYlZCTmkkSHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc5edbd7bb3e4377c6790f97d70f7b7a01cb78eb0a3facfb595840c482fb1950","last_reissued_at":"2026-07-05T02:49:35.038042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:35.038042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnivNet: A Neural Vocoder with Multi-Resolution Spectrogram Discriminators for High-Fidelity Waveform Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bongwan Kim, Dan Lim, Jaesam Yoon, Juntae Kim, Won Jang","submitted_at":"2021-06-15T05:35:34Z","abstract_excerpt":"Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models employing full-band mel-spectrograms, an over-smoothing problem occurs as part of which non-sharp spectrograms are generated. To address this problem, we propose UnivNet, a neural vocoder that synthesizes high-fidelity waveforms in real time. Inspired by works in the field of voice activity detection, we added a multi-resolution spectrogram discriminator that empl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07889","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/2106.07889/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":"2106.07889","created_at":"2026-07-05T02:49:35.038099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07889v1","created_at":"2026-07-05T02:49:35.038099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07889","created_at":"2026-07-05T02:49:35.038099+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RPNXV53HZBX","created_at":"2026-07-05T02:49:35.038099+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RPNXV53HZBXPRTZ","created_at":"2026-07-05T02:49:35.038099+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RPNXV53","created_at":"2026-07-05T02:49:35.038099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21372","citing_title":"NAC: Neural Action Codec for Vision-Language-Action Models","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30993","citing_title":"SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00861","citing_title":"Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI","json":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI.json","graph_json":"https://pith.science/api/pith-number/7RPNXV53HZBXPRTZB6L5OD33PI/graph.json","events_json":"https://pith.science/api/pith-number/7RPNXV53HZBXPRTZB6L5OD33PI/events.json","paper":"https://pith.science/paper/7RPNXV53"},"agent_actions":{"view_html":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI","download_json":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI.json","view_paper":"https://pith.science/paper/7RPNXV53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07889&json=true","fetch_graph":"https://pith.science/api/pith-number/7RPNXV53HZBXPRTZB6L5OD33PI/graph.json","fetch_events":"https://pith.science/api/pith-number/7RPNXV53HZBXPRTZB6L5OD33PI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI/action/storage_attestation","attest_author":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI/action/author_attestation","sign_citation":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI/action/citation_signature","submit_replication":"https://pith.science/pith/7RPNXV53HZBXPRTZB6L5OD33PI/action/replication_record"}},"created_at":"2026-07-05T02:49:35.038099+00:00","updated_at":"2026-07-05T02:49:35.038099+00:00"}