{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FOERN3JY6ZNOFUH5LIXMCFEOKS","short_pith_number":"pith:FOERN3JY","schema_version":"1.0","canonical_sha256":"2b8916ed38f65ae2d0fd5a2ec1148e548d96567f73042d801899e74d583767d7","source":{"kind":"arxiv","id":"1806.10522","version":2},"attestation_state":"computed","paper":{"title":"Speech Denoising with Deep Feature Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Francois G. Germain, Qifeng Chen, Vladlen Koltun","submitted_at":"2018-06-27T15:08:23Z","abstract_excerpt":"We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed signal that contains only the speech content. Recent approaches have shown promising results using various deep network architectures. In this paper, we propose to train a fully-convolutional context aggregation network using a deep feature loss. That loss is based on comparing the internal feature activations in a different network, trained for acoustic environ"},"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":"1806.10522","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-06-27T15:08:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"e867c83ae224ba6f722d5977e72ed785e223be268976756d4a81694b6d0de575","abstract_canon_sha256":"2aee945a8d5e4bb47fc27146aecbcf67a0ded37ff937adfa5ac8100d1e97f4e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:40.863187Z","signature_b64":"Z3QSs7qy18ftN2PRxWHWDj0o1Afs9lOMOWePedi+v2OjvYZR+0mbdIkgEsfFFqqC64olMyzmYvRlsA7UY7chDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b8916ed38f65ae2d0fd5a2ec1148e548d96567f73042d801899e74d583767d7","last_reissued_at":"2026-05-18T00:05:40.862295Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:40.862295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speech Denoising with Deep Feature Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Francois G. Germain, Qifeng Chen, Vladlen Koltun","submitted_at":"2018-06-27T15:08:23Z","abstract_excerpt":"We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed signal that contains only the speech content. Recent approaches have shown promising results using various deep network architectures. In this paper, we propose to train a fully-convolutional context aggregation network using a deep feature loss. That loss is based on comparing the internal feature activations in a different network, trained for acoustic environ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.10522","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":""},"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":"1806.10522","created_at":"2026-05-18T00:05:40.862467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.10522v2","created_at":"2026-05-18T00:05:40.862467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.10522","created_at":"2026-05-18T00:05:40.862467+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOERN3JY6ZNO","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOERN3JY6ZNOFUH5","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOERN3JY","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13387","citing_title":"Deep Speech Synthesis from Multimodal Articulatory Representations","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS","json":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS.json","graph_json":"https://pith.science/api/pith-number/FOERN3JY6ZNOFUH5LIXMCFEOKS/graph.json","events_json":"https://pith.science/api/pith-number/FOERN3JY6ZNOFUH5LIXMCFEOKS/events.json","paper":"https://pith.science/paper/FOERN3JY"},"agent_actions":{"view_html":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS","download_json":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS.json","view_paper":"https://pith.science/paper/FOERN3JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.10522&json=true","fetch_graph":"https://pith.science/api/pith-number/FOERN3JY6ZNOFUH5LIXMCFEOKS/graph.json","fetch_events":"https://pith.science/api/pith-number/FOERN3JY6ZNOFUH5LIXMCFEOKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS/action/storage_attestation","attest_author":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS/action/author_attestation","sign_citation":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS/action/citation_signature","submit_replication":"https://pith.science/pith/FOERN3JY6ZNOFUH5LIXMCFEOKS/action/replication_record"}},"created_at":"2026-05-18T00:05:40.862467+00:00","updated_at":"2026-05-18T00:05:40.862467+00:00"}