{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7TKVAVIOEDJYEUQFWBSG4TWKOE","short_pith_number":"pith:7TKVAVIO","schema_version":"1.0","canonical_sha256":"fcd550550e20d3825205b0646e4eca71161de4db6ace04a8ba6fa6c057baaaea","source":{"kind":"arxiv","id":"1811.08521","version":1},"attestation_state":"computed","paper":{"title":"Differentiable Consistency Constraints for Improved Deep Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Brian Patton, Jeremy Thorpe, John R. Hershey, Kevin Wilson, Michael Chinen, Rif A. Saurous, Scott Wisdom","submitted_at":"2018-11-20T22:44:12Z","abstract_excerpt":"In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to estimate masks for complex-valued short-time Fourier transforms (STFTs) to suppress noise and preserve speech. However, current masking approaches often neglect two important constraints: STFT consistency and mixture consistency. Without STFT consistency, the system's output is not necessarily the STFT of a time-domain signal, and without mixture consistenc"},"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":"1811.08521","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2018-11-20T22:44:12Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"95dfd5d5ea718dc2417dc7de4d8ef347ee9f64057fdff366a43d0e15e06b8f80","abstract_canon_sha256":"9fa9398da0a354675128356c936ef557614b2c4e3ec72327f9de0766f2345283"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:12.317694Z","signature_b64":"A213J5sK17fN7hqtzK7m9b1EJiqqQNyWfrqr9KCSG4qnF70eQGXwbSQdjzoIcA7r/3Atvw2wckrbf7LN3boWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd550550e20d3825205b0646e4eca71161de4db6ace04a8ba6fa6c057baaaea","last_reissued_at":"2026-05-18T00:00:12.317076Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:12.317076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Consistency Constraints for Improved Deep Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Brian Patton, Jeremy Thorpe, John R. Hershey, Kevin Wilson, Michael Chinen, Rif A. Saurous, Scott Wisdom","submitted_at":"2018-11-20T22:44:12Z","abstract_excerpt":"In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to estimate masks for complex-valued short-time Fourier transforms (STFTs) to suppress noise and preserve speech. However, current masking approaches often neglect two important constraints: STFT consistency and mixture consistency. Without STFT consistency, the system's output is not necessarily the STFT of a time-domain signal, and without mixture consistenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08521","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":""},"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":"1811.08521","created_at":"2026-05-18T00:00:12.317168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.08521v1","created_at":"2026-05-18T00:00:12.317168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08521","created_at":"2026-05-18T00:00:12.317168+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TKVAVIOEDJY","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TKVAVIOEDJYEUQF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TKVAVIO","created_at":"2026-05-18T12:32:11.075285+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/7TKVAVIOEDJYEUQFWBSG4TWKOE","json":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE.json","graph_json":"https://pith.science/api/pith-number/7TKVAVIOEDJYEUQFWBSG4TWKOE/graph.json","events_json":"https://pith.science/api/pith-number/7TKVAVIOEDJYEUQFWBSG4TWKOE/events.json","paper":"https://pith.science/paper/7TKVAVIO"},"agent_actions":{"view_html":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE","download_json":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE.json","view_paper":"https://pith.science/paper/7TKVAVIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.08521&json=true","fetch_graph":"https://pith.science/api/pith-number/7TKVAVIOEDJYEUQFWBSG4TWKOE/graph.json","fetch_events":"https://pith.science/api/pith-number/7TKVAVIOEDJYEUQFWBSG4TWKOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE/action/storage_attestation","attest_author":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE/action/author_attestation","sign_citation":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE/action/citation_signature","submit_replication":"https://pith.science/pith/7TKVAVIOEDJYEUQFWBSG4TWKOE/action/replication_record"}},"created_at":"2026-05-18T00:00:12.317168+00:00","updated_at":"2026-05-18T00:00:12.317168+00:00"}