{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JRNDELVTDJIIQN6X7I32NHVFQ5","short_pith_number":"pith:JRNDELVT","schema_version":"1.0","canonical_sha256":"4c5a322eb31a508837d7fa37a69ea58754debc56aa9efbc831bf7479fda9f3e1","source":{"kind":"arxiv","id":"2006.12847","version":3},"attestation_state":"computed","paper":{"title":"Real Time Speech Enhancement in the Waveform Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Alexandre Defossez, Gabriel Synnaeve, Yossi Adi","submitted_at":"2020-06-23T09:19:13Z","abstract_excerpt":"We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generali"},"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":"2006.12847","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-23T09:19:13Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"16b9d4005acf1b997e30d14ba16a1217b7c11a12a9daed99cf1d49c16af7d63c","abstract_canon_sha256":"be47a8c40faff76c9215f2e7cd8744a49286a3b1f82276d2472fe6786dcaeef7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:33:21.644966Z","signature_b64":"hbE8j6LhTmL8Pskpls+zAW7RlWDF78UQUFh7z3ap8sYPm84ZzrcvCBgNg3+nLFN3S0y5h8fiAUBZQ6aD2ZaxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c5a322eb31a508837d7fa37a69ea58754debc56aa9efbc831bf7479fda9f3e1","last_reissued_at":"2026-07-05T01:33:21.644493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:33:21.644493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real Time Speech Enhancement in the Waveform Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Alexandre Defossez, Gabriel Synnaeve, Yossi Adi","submitted_at":"2020-06-23T09:19:13Z","abstract_excerpt":"We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12847","kind":"arxiv","version":3},"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/2006.12847/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":"2006.12847","created_at":"2026-07-05T01:33:21.644558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12847v3","created_at":"2026-07-05T01:33:21.644558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12847","created_at":"2026-07-05T01:33:21.644558+00:00"},{"alias_kind":"pith_short_12","alias_value":"JRNDELVTDJII","created_at":"2026-07-05T01:33:21.644558+00:00"},{"alias_kind":"pith_short_16","alias_value":"JRNDELVTDJIIQN6X","created_at":"2026-07-05T01:33:21.644558+00:00"},{"alias_kind":"pith_short_8","alias_value":"JRNDELVT","created_at":"2026-07-05T01:33:21.644558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16681","citing_title":"A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12534","citing_title":"BioSEN: A Bio-acoustic Signal Enhancement Network for Animal Vocalizations","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12534","citing_title":"BioSEN: A Bio-acoustic Signal Enhancement Network for Animal Vocalizations","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2210.13438","citing_title":"High Fidelity Neural Audio Compression","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5","json":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5.json","graph_json":"https://pith.science/api/pith-number/JRNDELVTDJIIQN6X7I32NHVFQ5/graph.json","events_json":"https://pith.science/api/pith-number/JRNDELVTDJIIQN6X7I32NHVFQ5/events.json","paper":"https://pith.science/paper/JRNDELVT"},"agent_actions":{"view_html":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5","download_json":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5.json","view_paper":"https://pith.science/paper/JRNDELVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12847&json=true","fetch_graph":"https://pith.science/api/pith-number/JRNDELVTDJIIQN6X7I32NHVFQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/JRNDELVTDJIIQN6X7I32NHVFQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5/action/storage_attestation","attest_author":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5/action/author_attestation","sign_citation":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5/action/citation_signature","submit_replication":"https://pith.science/pith/JRNDELVTDJIIQN6X7I32NHVFQ5/action/replication_record"}},"created_at":"2026-07-05T01:33:21.644558+00:00","updated_at":"2026-07-05T01:33:21.644558+00:00"}