{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QGCGIOZ4WKAFRSJS25BCY3UOIG","short_pith_number":"pith:QGCGIOZ4","schema_version":"1.0","canonical_sha256":"8184643b3cb28058c932d7422c6e8e41882b7aab152c0a8b63da638f024d1a1b","source":{"kind":"arxiv","id":"2108.03342","version":1},"attestation_state":"computed","paper":{"title":"Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Desh Raj, Jun Du, Maokui He, Shinji Watanabe, Zhuo Chen, Zili Huang","submitted_at":"2021-08-07T01:29:37Z","abstract_excerpt":"Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fixed (and known) number of speakers, which limits its application to real conversations. In this paper, we extend TS-VAD to speaker diarization with unknown numbers of speakers. This is achieved by two steps: first, an initial diarization system is applied for speaker number estimation, followed by TS-VAD network output masking according to this estimate. We further investigate different diarization methods, including"},"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":"2108.03342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-07T01:29:37Z","cross_cats_sorted":[],"title_canon_sha256":"4b9ff5315765a4634e76e3d56759b107a922eda4141a79ef93cc8e5be125ac31","abstract_canon_sha256":"99b3433b334af7f3b4e72f3f7690db1e0de1ca7c2fcafbe7423d5385f49227dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:51.993972Z","signature_b64":"ifDKu1qldQ2nw1/4bueOnf5O6fCJR0ZsTzd+94xvi8vYrEQ7MUF+9zxqtsmgat154Gz62My2NBV04/qlg/xmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8184643b3cb28058c932d7422c6e8e41882b7aab152c0a8b63da638f024d1a1b","last_reissued_at":"2026-07-05T03:03:51.993477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:51.993477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Desh Raj, Jun Du, Maokui He, Shinji Watanabe, Zhuo Chen, Zili Huang","submitted_at":"2021-08-07T01:29:37Z","abstract_excerpt":"Target-speaker voice activity detection (TS-VAD) has recently shown promising results for speaker diarization on highly overlapped speech. However, the original model requires a fixed (and known) number of speakers, which limits its application to real conversations. In this paper, we extend TS-VAD to speaker diarization with unknown numbers of speakers. This is achieved by two steps: first, an initial diarization system is applied for speaker number estimation, followed by TS-VAD network output masking according to this estimate. We further investigate different diarization methods, including"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03342","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/2108.03342/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":"2108.03342","created_at":"2026-07-05T03:03:51.993537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.03342v1","created_at":"2026-07-05T03:03:51.993537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03342","created_at":"2026-07-05T03:03:51.993537+00:00"},{"alias_kind":"pith_short_12","alias_value":"QGCGIOZ4WKAF","created_at":"2026-07-05T03:03:51.993537+00:00"},{"alias_kind":"pith_short_16","alias_value":"QGCGIOZ4WKAFRSJS","created_at":"2026-07-05T03:03:51.993537+00:00"},{"alias_kind":"pith_short_8","alias_value":"QGCGIOZ4","created_at":"2026-07-05T03:03:51.993537+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/QGCGIOZ4WKAFRSJS25BCY3UOIG","json":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG.json","graph_json":"https://pith.science/api/pith-number/QGCGIOZ4WKAFRSJS25BCY3UOIG/graph.json","events_json":"https://pith.science/api/pith-number/QGCGIOZ4WKAFRSJS25BCY3UOIG/events.json","paper":"https://pith.science/paper/QGCGIOZ4"},"agent_actions":{"view_html":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG","download_json":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG.json","view_paper":"https://pith.science/paper/QGCGIOZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.03342&json=true","fetch_graph":"https://pith.science/api/pith-number/QGCGIOZ4WKAFRSJS25BCY3UOIG/graph.json","fetch_events":"https://pith.science/api/pith-number/QGCGIOZ4WKAFRSJS25BCY3UOIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/action/storage_attestation","attest_author":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/action/author_attestation","sign_citation":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/action/citation_signature","submit_replication":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/action/replication_record"}},"created_at":"2026-07-05T03:03:51.993537+00:00","updated_at":"2026-07-05T03:03:51.993537+00:00"}