{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:36LCZXVQA6USX23BVYYKLJWKE4","short_pith_number":"pith:36LCZXVQ","schema_version":"1.0","canonical_sha256":"df962cdeb007a92beb61ae30a5a6ca272db2f0174a0734bb4069232c3c1d07f8","source":{"kind":"arxiv","id":"2104.11347","version":2},"attestation_state":"computed","paper":{"title":"Restoring degraded speech via a modified diffusion model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianwei Zhang, Suren Jayasuriya, Visar Berisha","submitted_at":"2021-04-22T23:03:23Z","abstract_excerpt":"There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave model, that aims to restore the original speech signal. DiffWave, a recently published diffusion-based vocoder, has shown state-of-the-art synthesized speech quality and relatively shorter waveform generation times, with only a small set of parameters. We replace the mel-spectrum upsampler in DiffWave with a deep CNN upsampler, which is trained to alter the degr"},"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":"2104.11347","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-22T23:03:23Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"7d668f68a0e6075dbe63b1566817ad3e562afc0e586833443d82319cc7f85be2","abstract_canon_sha256":"b3bd16f06ae99f9089f7aae913960228bf593875d48465797630b7a7c9800705"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:06.209601Z","signature_b64":"a9T9+9rlTkapqPqHxdSSKcemeg4JXydUt56jA5cOhErY7f3YAWduevOC1xyBejHvQJAbHMEYf196g9oSeTJzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df962cdeb007a92beb61ae30a5a6ca272db2f0174a0734bb4069232c3c1d07f8","last_reissued_at":"2026-07-05T03:11:06.209177Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:06.209177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Restoring degraded speech via a modified diffusion model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianwei Zhang, Suren Jayasuriya, Visar Berisha","submitted_at":"2021-04-22T23:03:23Z","abstract_excerpt":"There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification of the DiffWave model, that aims to restore the original speech signal. DiffWave, a recently published diffusion-based vocoder, has shown state-of-the-art synthesized speech quality and relatively shorter waveform generation times, with only a small set of parameters. We replace the mel-spectrum upsampler in DiffWave with a deep CNN upsampler, which is trained to alter the degr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11347","kind":"arxiv","version":2},"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/2104.11347/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":"2104.11347","created_at":"2026-07-05T03:11:06.209232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.11347v2","created_at":"2026-07-05T03:11:06.209232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11347","created_at":"2026-07-05T03:11:06.209232+00:00"},{"alias_kind":"pith_short_12","alias_value":"36LCZXVQA6US","created_at":"2026-07-05T03:11:06.209232+00:00"},{"alias_kind":"pith_short_16","alias_value":"36LCZXVQA6USX23B","created_at":"2026-07-05T03:11:06.209232+00:00"},{"alias_kind":"pith_short_8","alias_value":"36LCZXVQ","created_at":"2026-07-05T03:11:06.209232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15254","citing_title":"Voice-ENHANCE: Speech Restoration using a Diffusion-based Voice Conversion Framework","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4","json":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4.json","graph_json":"https://pith.science/api/pith-number/36LCZXVQA6USX23BVYYKLJWKE4/graph.json","events_json":"https://pith.science/api/pith-number/36LCZXVQA6USX23BVYYKLJWKE4/events.json","paper":"https://pith.science/paper/36LCZXVQ"},"agent_actions":{"view_html":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4","download_json":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4.json","view_paper":"https://pith.science/paper/36LCZXVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.11347&json=true","fetch_graph":"https://pith.science/api/pith-number/36LCZXVQA6USX23BVYYKLJWKE4/graph.json","fetch_events":"https://pith.science/api/pith-number/36LCZXVQA6USX23BVYYKLJWKE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4/action/storage_attestation","attest_author":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4/action/author_attestation","sign_citation":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4/action/citation_signature","submit_replication":"https://pith.science/pith/36LCZXVQA6USX23BVYYKLJWKE4/action/replication_record"}},"created_at":"2026-07-05T03:11:06.209232+00:00","updated_at":"2026-07-05T03:11:06.209232+00:00"}