{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VWCMDDHEUW4TDZR2VVQ6L2LSAX","short_pith_number":"pith:VWCMDDHE","schema_version":"1.0","canonical_sha256":"ad84c18ce4a5b931e63aad61e5e97205c81268de529ab6d01bb53b3757389c84","source":{"kind":"arxiv","id":"2409.06274","version":1},"attestation_state":"computed","paper":{"title":"Spectral oversubtraction? An approach for speech enhancement after robot ego speech filtering in semi-real-time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.RO","authors_text":"Florian A. Kunneman, Koen V. Hindriks, Yue Li","submitted_at":"2024-09-10T07:24:35Z","abstract_excerpt":"Spectral subtraction, widely used for its simplicity, has been employed to address the Robot Ego Speech Filtering (RESF) problem for detecting speech contents of human interruption from robot's single-channel microphone recordings when it is speaking. However, this approach suffers from oversubtraction in the fundamental frequency range (FFR), leading to degraded speech content recognition. To address this, we propose a Two-Mask Conformer-based Metric Generative Adversarial Network (CMGAN) to enhance the detected speech and improve recognition results. Our model compensates for oversubtracted "},"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":"2409.06274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-10T07:24:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"8d23d36edaebee2c1105612534ba35f385ee6cfac764354b618882c13445e093","abstract_canon_sha256":"2eca327c10bf9c47231067cab90d83e1c26594b36f220d5aa10e837376b38529"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:21.753745Z","signature_b64":"c+bs4Up8oMwo/rcn2VTGB0/qZ6w/wXeL/+obrk/E3MP4+DHTgGtAjH2ZCMrTrUxqc7dnz02Faw3g8k0plfeIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad84c18ce4a5b931e63aad61e5e97205c81268de529ab6d01bb53b3757389c84","last_reissued_at":"2026-07-05T09:05:21.753344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:21.753344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral oversubtraction? An approach for speech enhancement after robot ego speech filtering in semi-real-time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.RO","authors_text":"Florian A. Kunneman, Koen V. Hindriks, Yue Li","submitted_at":"2024-09-10T07:24:35Z","abstract_excerpt":"Spectral subtraction, widely used for its simplicity, has been employed to address the Robot Ego Speech Filtering (RESF) problem for detecting speech contents of human interruption from robot's single-channel microphone recordings when it is speaking. However, this approach suffers from oversubtraction in the fundamental frequency range (FFR), leading to degraded speech content recognition. To address this, we propose a Two-Mask Conformer-based Metric Generative Adversarial Network (CMGAN) to enhance the detected speech and improve recognition results. Our model compensates for oversubtracted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.06274","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.06274/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":"2409.06274","created_at":"2026-07-05T09:05:21.753405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.06274v1","created_at":"2026-07-05T09:05:21.753405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.06274","created_at":"2026-07-05T09:05:21.753405+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWCMDDHEUW4T","created_at":"2026-07-05T09:05:21.753405+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWCMDDHEUW4TDZR2","created_at":"2026-07-05T09:05:21.753405+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWCMDDHE","created_at":"2026-07-05T09:05:21.753405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23515","citing_title":"DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX","json":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX.json","graph_json":"https://pith.science/api/pith-number/VWCMDDHEUW4TDZR2VVQ6L2LSAX/graph.json","events_json":"https://pith.science/api/pith-number/VWCMDDHEUW4TDZR2VVQ6L2LSAX/events.json","paper":"https://pith.science/paper/VWCMDDHE"},"agent_actions":{"view_html":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX","download_json":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX.json","view_paper":"https://pith.science/paper/VWCMDDHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.06274&json=true","fetch_graph":"https://pith.science/api/pith-number/VWCMDDHEUW4TDZR2VVQ6L2LSAX/graph.json","fetch_events":"https://pith.science/api/pith-number/VWCMDDHEUW4TDZR2VVQ6L2LSAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX/action/storage_attestation","attest_author":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX/action/author_attestation","sign_citation":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX/action/citation_signature","submit_replication":"https://pith.science/pith/VWCMDDHEUW4TDZR2VVQ6L2LSAX/action/replication_record"}},"created_at":"2026-07-05T09:05:21.753405+00:00","updated_at":"2026-07-05T09:05:21.753405+00:00"}