{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JOMNKNS2RISW3L5IZRK5J244TS","short_pith_number":"pith:JOMNKNS2","schema_version":"1.0","canonical_sha256":"4b98d5365a8a256dafa8cc55d4eb9c9c8497c1109cf1d6de3c2cbabec3e17c11","source":{"kind":"arxiv","id":"2501.03184","version":1},"attestation_state":"computed","paper":{"title":"Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"2), (2) Oticon A/S), Holger Severin Bovbjerg (1), Jan {\\O}stergaard (1), Jesper Jensen (1, Zheng-Hua Tan (1) ((1) Aalborg University","submitted_at":"2025-01-06T18:00:14Z","abstract_excerpt":"Target-Speaker Voice Activity Detection (TS-VAD) is the task of detecting the presence of speech from a known target-speaker in an audio frame. Recently, deep neural network-based models have shown good performance in this task. However, training these models requires extensive labelled data, which is costly and time-consuming to obtain, particularly if generalization to unseen environments is crucial. To mitigate this, we propose a causal, Self-Supervised Learning (SSL) pretraining framework, called Denoising Autoregressive Predictive Coding (DN-APC), to enhance TS-VAD performance in noisy co"},"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":"2501.03184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-06T18:00:14Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"642856e29bb3c9509cb21ab443236ae90357387d3159e7ea72f6ba39ce529f18","abstract_canon_sha256":"144698340a67ab42daca5bb5a7b7d8d3b9f46cf0b48fcb0967988ced16ec7286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:32.842385Z","signature_b64":"kwVGUHqE61O6SwUMlYpi7xn+p/vmfyV71zJ8RTq987pbGwIAlb4j/4shxCYQUBmNI+ObwMhC2RIouuW7GD4bCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b98d5365a8a256dafa8cc55d4eb9c9c8497c1109cf1d6de3c2cbabec3e17c11","last_reissued_at":"2026-07-05T09:57:32.841906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:32.841906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"2), (2) Oticon A/S), Holger Severin Bovbjerg (1), Jan {\\O}stergaard (1), Jesper Jensen (1, Zheng-Hua Tan (1) ((1) Aalborg University","submitted_at":"2025-01-06T18:00:14Z","abstract_excerpt":"Target-Speaker Voice Activity Detection (TS-VAD) is the task of detecting the presence of speech from a known target-speaker in an audio frame. Recently, deep neural network-based models have shown good performance in this task. However, training these models requires extensive labelled data, which is costly and time-consuming to obtain, particularly if generalization to unseen environments is crucial. To mitigate this, we propose a causal, Self-Supervised Learning (SSL) pretraining framework, called Denoising Autoregressive Predictive Coding (DN-APC), to enhance TS-VAD performance in noisy co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03184","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/2501.03184/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":"2501.03184","created_at":"2026-07-05T09:57:32.841959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03184v1","created_at":"2026-07-05T09:57:32.841959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03184","created_at":"2026-07-05T09:57:32.841959+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOMNKNS2RISW","created_at":"2026-07-05T09:57:32.841959+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOMNKNS2RISW3L5I","created_at":"2026-07-05T09:57:32.841959+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOMNKNS2","created_at":"2026-07-05T09:57:32.841959+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/JOMNKNS2RISW3L5IZRK5J244TS","json":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS.json","graph_json":"https://pith.science/api/pith-number/JOMNKNS2RISW3L5IZRK5J244TS/graph.json","events_json":"https://pith.science/api/pith-number/JOMNKNS2RISW3L5IZRK5J244TS/events.json","paper":"https://pith.science/paper/JOMNKNS2"},"agent_actions":{"view_html":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS","download_json":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS.json","view_paper":"https://pith.science/paper/JOMNKNS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03184&json=true","fetch_graph":"https://pith.science/api/pith-number/JOMNKNS2RISW3L5IZRK5J244TS/graph.json","fetch_events":"https://pith.science/api/pith-number/JOMNKNS2RISW3L5IZRK5J244TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS/action/storage_attestation","attest_author":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS/action/author_attestation","sign_citation":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS/action/citation_signature","submit_replication":"https://pith.science/pith/JOMNKNS2RISW3L5IZRK5J244TS/action/replication_record"}},"created_at":"2026-07-05T09:57:32.841959+00:00","updated_at":"2026-07-05T09:57:32.841959+00:00"}