{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QOZI32NUI3DAKK3I4NZ72GKJMP","short_pith_number":"pith:QOZI32NU","schema_version":"1.0","canonical_sha256":"83b28de9b446c6052b68e373fd194963c0cc09caced60d209fea51bed2549f33","source":{"kind":"arxiv","id":"2606.23332","version":1},"attestation_state":"computed","paper":{"title":"Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexander Neergaard Zahid, Andreas Hansen Bagge, Karl Ulb{\\ae}k, Kenny Falk{\\ae}r Olsen, Mads {\\O}stergaard, Rasmus Malik H{\\o}egh Lindrup","submitted_at":"2026-06-22T13:41:24Z","abstract_excerpt":"We introduce own-voice cancellation (OVC): removing a target (enrolled) speaker from a noisy multi-speaker mixture while preserving any remaining speech. Framed as the complement of target speaker extraction, OVC addresses latency-induced own-voice artifacts that arise when a far-field device streams enhanced audio back to the user, as the round-trip time easily exceeds the perceptual threshold for own-voice distortion. We condition a time-domain model with only 2 ms algorithmic latency on a short enrollment utterance and benchmark TD-SpeakerBeam alongside a lighter Mamba-MinGRU masker built f"},"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":"2606.23332","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-22T13:41:24Z","cross_cats_sorted":[],"title_canon_sha256":"1187049e5de568e4656223a8a8690a8761a679008003b36a835c9919cfc9066e","abstract_canon_sha256":"4c04da2779846f123112c358311612808e6618881d71fbe766bdd874fec12532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:17.024094Z","signature_b64":"kdIO5qBnA7tqB5dv97d0MkgdCCoP40bqfT3IIEyePdoRUyK6k8nbBmk7uTEp4SkNJ/B6VoloZtX3t4KS9wZdAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83b28de9b446c6052b68e373fd194963c0cc09caced60d209fea51bed2549f33","last_reissued_at":"2026-06-23T03:14:17.023728Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:17.023728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Alexander Neergaard Zahid, Andreas Hansen Bagge, Karl Ulb{\\ae}k, Kenny Falk{\\ae}r Olsen, Mads {\\O}stergaard, Rasmus Malik H{\\o}egh Lindrup","submitted_at":"2026-06-22T13:41:24Z","abstract_excerpt":"We introduce own-voice cancellation (OVC): removing a target (enrolled) speaker from a noisy multi-speaker mixture while preserving any remaining speech. Framed as the complement of target speaker extraction, OVC addresses latency-induced own-voice artifacts that arise when a far-field device streams enhanced audio back to the user, as the round-trip time easily exceeds the perceptual threshold for own-voice distortion. We condition a time-domain model with only 2 ms algorithmic latency on a short enrollment utterance and benchmark TD-SpeakerBeam alongside a lighter Mamba-MinGRU masker built f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23332","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/2606.23332/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":"2606.23332","created_at":"2026-06-23T03:14:17.023785+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23332v1","created_at":"2026-06-23T03:14:17.023785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23332","created_at":"2026-06-23T03:14:17.023785+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOZI32NUI3DA","created_at":"2026-06-23T03:14:17.023785+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOZI32NUI3DAKK3I","created_at":"2026-06-23T03:14:17.023785+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOZI32NU","created_at":"2026-06-23T03:14:17.023785+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.23332","citing_title":"Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP","json":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP.json","graph_json":"https://pith.science/api/pith-number/QOZI32NUI3DAKK3I4NZ72GKJMP/graph.json","events_json":"https://pith.science/api/pith-number/QOZI32NUI3DAKK3I4NZ72GKJMP/events.json","paper":"https://pith.science/paper/QOZI32NU"},"agent_actions":{"view_html":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP","download_json":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP.json","view_paper":"https://pith.science/paper/QOZI32NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23332&json=true","fetch_graph":"https://pith.science/api/pith-number/QOZI32NUI3DAKK3I4NZ72GKJMP/graph.json","fetch_events":"https://pith.science/api/pith-number/QOZI32NUI3DAKK3I4NZ72GKJMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP/action/storage_attestation","attest_author":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP/action/author_attestation","sign_citation":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP/action/citation_signature","submit_replication":"https://pith.science/pith/QOZI32NUI3DAKK3I4NZ72GKJMP/action/replication_record"}},"created_at":"2026-06-23T03:14:17.023785+00:00","updated_at":"2026-06-23T03:14:17.023785+00:00"}