{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5W3MTHSETZIZZXK7E4MQR6CHNG","short_pith_number":"pith:5W3MTHSE","schema_version":"1.0","canonical_sha256":"edb6c99e449e519cdd5f271908f84769861ca525f4e95b105f8bef0ad298f114","source":{"kind":"arxiv","id":"2004.04098","version":3},"attestation_state":"computed","paper":{"title":"WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hsin-Min Wang, Tsun-An Hsieh, Xugang Lu, Yu Tsao","submitted_at":"2020-04-06T13:48:05Z","abstract_excerpt":"Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the locality and temporal sequential properties of speech should be efficiently taken into account when modelling. However, in most current E2E models for SE, these properties are either not fully considered or are too complex to be realized. In this paper, we propose an efficient E2E SE model, termed WaveCRN. In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the tempor"},"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":"2004.04098","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-04-06T13:48:05Z","cross_cats_sorted":["cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"db78c4b67be59c9297ea5a02032b869236b6da144da6e17b9b8b7153db1ea932","abstract_canon_sha256":"3eee910453e187b34941484531fd2af18d33175b98e112d9189b96dd4808072e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:46.387053Z","signature_b64":"PP26eJS0sKFr5J4uC72PJO3Om9T0YUXub9kfBBBsSXcuG/4CmkH2JshCYgO5kTK7R0ii4pvMBU6FK/cPKiKUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edb6c99e449e519cdd5f271908f84769861ca525f4e95b105f8bef0ad298f114","last_reissued_at":"2026-07-05T02:11:46.386615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:46.386615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WaveCRN: An Efficient Convolutional Recurrent Neural Network for End-to-end Speech Enhancement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Hsin-Min Wang, Tsun-An Hsieh, Xugang Lu, Yu Tsao","submitted_at":"2020-04-06T13:48:05Z","abstract_excerpt":"Due to the simple design pipeline, end-to-end (E2E) neural models for speech enhancement (SE) have attracted great interest. In order to improve the performance of the E2E model, the locality and temporal sequential properties of speech should be efficiently taken into account when modelling. However, in most current E2E models for SE, these properties are either not fully considered or are too complex to be realized. In this paper, we propose an efficient E2E SE model, termed WaveCRN. In WaveCRN, the speech locality feature is captured by a convolutional neural network (CNN), while the tempor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.04098","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/2004.04098/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":"2004.04098","created_at":"2026-07-05T02:11:46.386664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.04098v3","created_at":"2026-07-05T02:11:46.386664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04098","created_at":"2026-07-05T02:11:46.386664+00:00"},{"alias_kind":"pith_short_12","alias_value":"5W3MTHSETZIZ","created_at":"2026-07-05T02:11:46.386664+00:00"},{"alias_kind":"pith_short_16","alias_value":"5W3MTHSETZIZZXK7","created_at":"2026-07-05T02:11:46.386664+00:00"},{"alias_kind":"pith_short_8","alias_value":"5W3MTHSE","created_at":"2026-07-05T02:11:46.386664+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/5W3MTHSETZIZZXK7E4MQR6CHNG","json":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG.json","graph_json":"https://pith.science/api/pith-number/5W3MTHSETZIZZXK7E4MQR6CHNG/graph.json","events_json":"https://pith.science/api/pith-number/5W3MTHSETZIZZXK7E4MQR6CHNG/events.json","paper":"https://pith.science/paper/5W3MTHSE"},"agent_actions":{"view_html":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG","download_json":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG.json","view_paper":"https://pith.science/paper/5W3MTHSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.04098&json=true","fetch_graph":"https://pith.science/api/pith-number/5W3MTHSETZIZZXK7E4MQR6CHNG/graph.json","fetch_events":"https://pith.science/api/pith-number/5W3MTHSETZIZZXK7E4MQR6CHNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG/action/storage_attestation","attest_author":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG/action/author_attestation","sign_citation":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG/action/citation_signature","submit_replication":"https://pith.science/pith/5W3MTHSETZIZZXK7E4MQR6CHNG/action/replication_record"}},"created_at":"2026-07-05T02:11:46.386664+00:00","updated_at":"2026-07-05T02:11:46.386664+00:00"}