{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QGCGIOZ4WKAFRSJS25BCY3UOIG","short_pith_number":"pith:QGCGIOZ4","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"},"canonical_sha256":"8184643b3cb28058c932d7422c6e8e41882b7aab152c0a8b63da638f024d1a1b","source":{"kind":"arxiv","id":"2108.03342","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03342","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03342v1","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03342","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"QGCGIOZ4WKAF","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"QGCGIOZ4WKAFRSJS","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"QGCGIOZ4","created_at":"2026-07-05T03:03:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QGCGIOZ4WKAFRSJS25BCY3UOIG","target":"record","payload":{"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"},"canonical_sha256":"8184643b3cb28058c932d7422c6e8e41882b7aab152c0a8b63da638f024d1a1b","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"},"source_kind":"arxiv","source_id":"2108.03342","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:03:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1VPPQ3sLUExeKxIxwQrB8I8sT3n1tMuGlE/WdFugp6okNEY722PwKR8xVJHMSKEI+d1Vb4JF5uQZgIHUdoDcCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:12:22.043943Z"},"content_sha256":"980c3b9bd1a2d8e7751e088bf3137baed07cf22a9d248ef8e2879f45a26b79de","schema_version":"1.0","event_id":"sha256:980c3b9bd1a2d8e7751e088bf3137baed07cf22a9d248ef8e2879f45a26b79de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QGCGIOZ4WKAFRSJS25BCY3UOIG","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:03:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xIYnPeIJwyp73JF3s4LqWNOKHxNIqrWlFxFqhZboKzaBlFLlDuJ+A4MXmBByMqKDa+zlGz7lkv1fbLDNEeYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T21:12:22.044325Z"},"content_sha256":"9eadeab289bd0b44b9dd1cc09b54ca61420ca19f498e767c879353abb30a158a","schema_version":"1.0","event_id":"sha256:9eadeab289bd0b44b9dd1cc09b54ca61420ca19f498e767c879353abb30a158a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/bundle.json","state_url":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T21:12:22Z","links":{"resolver":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG","bundle":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/bundle.json","state":"https://pith.science/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGCGIOZ4WKAFRSJS25BCY3UOIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QGCGIOZ4WKAFRSJS25BCY3UOIG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"99b3433b334af7f3b4e72f3f7690db1e0de1ca7c2fcafbe7423d5385f49227dc","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-07T01:29:37Z","title_canon_sha256":"4b9ff5315765a4634e76e3d56759b107a922eda4141a79ef93cc8e5be125ac31"},"schema_version":"1.0","source":{"id":"2108.03342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03342","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03342v1","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03342","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"pith_short_12","alias_value":"QGCGIOZ4WKAF","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"pith_short_16","alias_value":"QGCGIOZ4WKAFRSJS","created_at":"2026-07-05T03:03:51Z"},{"alias_kind":"pith_short_8","alias_value":"QGCGIOZ4","created_at":"2026-07-05T03:03:51Z"}],"graph_snapshots":[{"event_id":"sha256:9eadeab289bd0b44b9dd1cc09b54ca61420ca19f498e767c879353abb30a158a","target":"graph","created_at":"2026-07-05T03:03:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.03342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Desh Raj, Jun Du, Maokui He, Shinji Watanabe, Zhuo Chen, Zili Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-07T01:29:37Z","title":"Target-speaker Voice Activity Detection with Improved I-Vector Estimation for Unknown Number of Speaker"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03342","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:980c3b9bd1a2d8e7751e088bf3137baed07cf22a9d248ef8e2879f45a26b79de","target":"record","created_at":"2026-07-05T03:03:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"99b3433b334af7f3b4e72f3f7690db1e0de1ca7c2fcafbe7423d5385f49227dc","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2021-08-07T01:29:37Z","title_canon_sha256":"4b9ff5315765a4634e76e3d56759b107a922eda4141a79ef93cc8e5be125ac31"},"schema_version":"1.0","source":{"id":"2108.03342","kind":"arxiv","version":1}},"canonical_sha256":"8184643b3cb28058c932d7422c6e8e41882b7aab152c0a8b63da638f024d1a1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8184643b3cb28058c932d7422c6e8e41882b7aab152c0a8b63da638f024d1a1b","first_computed_at":"2026-07-05T03:03:51.993477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:51.993477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ifDKu1qldQ2nw1/4bueOnf5O6fCJR0ZsTzd+94xvi8vYrEQ7MUF+9zxqtsmgat154Gz62My2NBV04/qlg/xmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:51.993972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.03342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:980c3b9bd1a2d8e7751e088bf3137baed07cf22a9d248ef8e2879f45a26b79de","sha256:9eadeab289bd0b44b9dd1cc09b54ca61420ca19f498e767c879353abb30a158a"],"state_sha256":"ff9e45e4104bd8a316887d181686e27be7ecbe810c343a88e41307e458dcf64e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqvN53dQPk4WHEuTbCsj6bTFj8urXb9jb+bW2XQkALOxPUZJy1oOjUgdWM36Z/6H8pgeYrYuR9ZBKKCLYeaCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T21:12:22.046241Z","bundle_sha256":"40541567e21d3982927c51dfdcf80921785ad4903c16ec832543aa176a008a8c"}}