{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VR5URISY25XIJZIGASNHIZB55E","short_pith_number":"pith:VR5URISY","schema_version":"1.0","canonical_sha256":"ac7b48a258d76e84e506049a74643de91af25c6f9c566da5ccabfbf57fd4942f","source":{"kind":"arxiv","id":"2101.05516","version":2},"attestation_state":"computed","paper":{"title":"Speaker activity driven neural speech extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Katerina Zmolikova, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Tsubasa Ochiai","submitted_at":"2021-01-14T09:21:51Z","abstract_excerpt":"Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In this paper, we explore the use of speaker activity information as an auxiliary clue for single-channel neural network-based speech extraction. We propose a speaker activity driven speech extraction neural network (ADEnet) and show that it can achieve performance levels competitive with enrollment-based"},"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":"2101.05516","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-01-14T09:21:51Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0f261786fbc739d2230f60713d6a5bd336d27cfb400446648b13b0428b341464","abstract_canon_sha256":"c665fdbf2100d8a4f5eb57f445c3bccb5344a301ee19c3727fe06132ab951bd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:13.714092Z","signature_b64":"Bc93EIKx4IZ2S7a6AIRx3o57j7fiSEHpv2NZieVMwZ44J7qgab+4mbvXNYLLd04Lx3Jk7GSwvOkqSoQ/s3TWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac7b48a258d76e84e506049a74643de91af25c6f9c566da5ccabfbf57fd4942f","last_reissued_at":"2026-07-05T02:14:13.713682Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:13.713682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker activity driven neural speech extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Katerina Zmolikova, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Tsubasa Ochiai","submitted_at":"2021-01-14T09:21:51Z","abstract_excerpt":"Target speech extraction, which extracts the speech of a target speaker in a mixture given auxiliary speaker clues, has recently received increased interest. Various clues have been investigated such as pre-recorded enrollment utterances, direction information, or video of the target speaker. In this paper, we explore the use of speaker activity information as an auxiliary clue for single-channel neural network-based speech extraction. We propose a speaker activity driven speech extraction neural network (ADEnet) and show that it can achieve performance levels competitive with enrollment-based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.05516","kind":"arxiv","version":2},"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/2101.05516/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":"2101.05516","created_at":"2026-07-05T02:14:13.713740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.05516v2","created_at":"2026-07-05T02:14:13.713740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.05516","created_at":"2026-07-05T02:14:13.713740+00:00"},{"alias_kind":"pith_short_12","alias_value":"VR5URISY25XI","created_at":"2026-07-05T02:14:13.713740+00:00"},{"alias_kind":"pith_short_16","alias_value":"VR5URISY25XIJZIG","created_at":"2026-07-05T02:14:13.713740+00:00"},{"alias_kind":"pith_short_8","alias_value":"VR5URISY","created_at":"2026-07-05T02:14:13.713740+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/VR5URISY25XIJZIGASNHIZB55E","json":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E.json","graph_json":"https://pith.science/api/pith-number/VR5URISY25XIJZIGASNHIZB55E/graph.json","events_json":"https://pith.science/api/pith-number/VR5URISY25XIJZIGASNHIZB55E/events.json","paper":"https://pith.science/paper/VR5URISY"},"agent_actions":{"view_html":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E","download_json":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E.json","view_paper":"https://pith.science/paper/VR5URISY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.05516&json=true","fetch_graph":"https://pith.science/api/pith-number/VR5URISY25XIJZIGASNHIZB55E/graph.json","fetch_events":"https://pith.science/api/pith-number/VR5URISY25XIJZIGASNHIZB55E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E/action/storage_attestation","attest_author":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E/action/author_attestation","sign_citation":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E/action/citation_signature","submit_replication":"https://pith.science/pith/VR5URISY25XIJZIGASNHIZB55E/action/replication_record"}},"created_at":"2026-07-05T02:14:13.713740+00:00","updated_at":"2026-07-05T02:14:13.713740+00:00"}