{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EF5G2XVKUHRMMBLUT36YC5ZNFT","short_pith_number":"pith:EF5G2XVK","schema_version":"1.0","canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","source":{"kind":"arxiv","id":"2409.04859","version":2},"attestation_state":"computed","paper":{"title":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Yidi Jiang, Zhengyang Chen","submitted_at":"2024-09-07T15:38:28Z","abstract_excerpt":"Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, w"},"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":"2409.04859","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-07T15:38:28Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b7558eea0cf9ae93f41a3825186295ecc1631b4f2ef87cbc209490cac89d2159","abstract_canon_sha256":"3e0d3ac28e0a2f2baf509170813b31b7978c36bfd70e76c5868bfbdb822f1dd2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:06.505440Z","signature_b64":"Ee1KFSm0Z1SsTLAQgTgap6su1R1BefN3rY6hCfmwrYkppBHW/3Fd2r4TLZx1Rda3jt89h2wJwI8IQiUB+V7xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"217a6d5eaaa1e2c605749efd81772d2cedafa1ffa9693e7c7d4fda25c8632437","last_reissued_at":"2026-07-05T09:09:06.504959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:06.504959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow-TSVAD: Target-Speaker Voice Activity Detection via Latent Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bing Han, Shuai Wang, Yanmin Qian, Yidi Jiang, Zhengyang Chen","submitted_at":"2024-09-07T15:38:28Z","abstract_excerpt":"Speaker diarization is typically considered a discriminative task, using discriminative approaches to produce fixed diarization results. In this paper, we explore the use of neural network-based generative methods for speaker diarization for the first time. We implement a Flow-Matching (FM) based generative algorithm within the sequence-to-sequence target speaker voice activity detection (Seq2Seq-TSVAD) diarization system. Our experiments reveal that applying the generative method directly to the original binary label sequence space of the TS-VAD output is ineffective. To address this issue, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04859","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/2409.04859/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":"2409.04859","created_at":"2026-07-05T09:09:06.505015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04859v2","created_at":"2026-07-05T09:09:06.505015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04859","created_at":"2026-07-05T09:09:06.505015+00:00"},{"alias_kind":"pith_short_12","alias_value":"EF5G2XVKUHRM","created_at":"2026-07-05T09:09:06.505015+00:00"},{"alias_kind":"pith_short_16","alias_value":"EF5G2XVKUHRMMBLU","created_at":"2026-07-05T09:09:06.505015+00:00"},{"alias_kind":"pith_short_8","alias_value":"EF5G2XVK","created_at":"2026-07-05T09:09:06.505015+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/EF5G2XVKUHRMMBLUT36YC5ZNFT","json":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT.json","graph_json":"https://pith.science/api/pith-number/EF5G2XVKUHRMMBLUT36YC5ZNFT/graph.json","events_json":"https://pith.science/api/pith-number/EF5G2XVKUHRMMBLUT36YC5ZNFT/events.json","paper":"https://pith.science/paper/EF5G2XVK"},"agent_actions":{"view_html":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT","download_json":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT.json","view_paper":"https://pith.science/paper/EF5G2XVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04859&json=true","fetch_graph":"https://pith.science/api/pith-number/EF5G2XVKUHRMMBLUT36YC5ZNFT/graph.json","fetch_events":"https://pith.science/api/pith-number/EF5G2XVKUHRMMBLUT36YC5ZNFT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/action/storage_attestation","attest_author":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/action/author_attestation","sign_citation":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/action/citation_signature","submit_replication":"https://pith.science/pith/EF5G2XVKUHRMMBLUT36YC5ZNFT/action/replication_record"}},"created_at":"2026-07-05T09:09:06.505015+00:00","updated_at":"2026-07-05T09:09:06.505015+00:00"}