{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WH7U2LCA7KPPY7A5HGTZO4T7IQ","short_pith_number":"pith:WH7U2LCA","schema_version":"1.0","canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","source":{"kind":"arxiv","id":"2101.08473","version":2},"attestation_state":"computed","paper":{"title":"Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kenji Nagamatsu, Paola Garcia, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Yuki Takashima, Yusuke Fujita","submitted_at":"2021-01-21T07:24:21Z","abstract_excerpt":"We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was proposed to achieve a chunk-wise streaming diarization using a pre-trained EEND model. STB traces the speaker information in previous chunks to map the speakers in a new chunk. However, it only worked with two-speaker recordings. In this paper, we propose an extended STB for flexible numbers of speakers, FLEX-STB. The proposed method uses a zero-padding followed "},"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":"2101.08473","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-01-21T07:24:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"11334201cfb3aa6cc2e80b3d37eb13a5dfa604a4e1afd1bd748c0e0e35e1d246","abstract_canon_sha256":"f66d7f59196173e3a4bd58e4c29f94a3603e0162fbe05f98133375f501eecf5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:57.078881Z","signature_b64":"jAEgHN10HLttGSd7GPVswAlRZnTb7V7m5zGvvxMRz87WMWepYkS8NmtsD/nlpzVKAPTbYUxBuXa28TAgqMDXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ff4d2c40fa9efc7c1d39a797727f44015973603a07ab7b8b6424edc92935da","last_reissued_at":"2026-07-05T02:29:57.078434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:57.078434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kenji Nagamatsu, Paola Garcia, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Yuki Takashima, Yusuke Fujita","submitted_at":"2021-01-21T07:24:21Z","abstract_excerpt":"We propose a streaming diarization method based on an end-to-end neural diarization (EEND) model, which handles flexible numbers of speakers and overlapping speech. In our previous study, the speaker-tracing buffer (STB) mechanism was proposed to achieve a chunk-wise streaming diarization using a pre-trained EEND model. STB traces the speaker information in previous chunks to map the speakers in a new chunk. However, it only worked with two-speaker recordings. In this paper, we propose an extended STB for flexible numbers of speakers, FLEX-STB. The proposed method uses a zero-padding followed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08473","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/2101.08473/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":"2101.08473","created_at":"2026-07-05T02:29:57.078489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08473v2","created_at":"2026-07-05T02:29:57.078489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08473","created_at":"2026-07-05T02:29:57.078489+00:00"},{"alias_kind":"pith_short_12","alias_value":"WH7U2LCA7KPP","created_at":"2026-07-05T02:29:57.078489+00:00"},{"alias_kind":"pith_short_16","alias_value":"WH7U2LCA7KPPY7A5","created_at":"2026-07-05T02:29:57.078489+00:00"},{"alias_kind":"pith_short_8","alias_value":"WH7U2LCA","created_at":"2026-07-05T02:29:57.078489+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/WH7U2LCA7KPPY7A5HGTZO4T7IQ","json":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ.json","graph_json":"https://pith.science/api/pith-number/WH7U2LCA7KPPY7A5HGTZO4T7IQ/graph.json","events_json":"https://pith.science/api/pith-number/WH7U2LCA7KPPY7A5HGTZO4T7IQ/events.json","paper":"https://pith.science/paper/WH7U2LCA"},"agent_actions":{"view_html":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ","download_json":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ.json","view_paper":"https://pith.science/paper/WH7U2LCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08473&json=true","fetch_graph":"https://pith.science/api/pith-number/WH7U2LCA7KPPY7A5HGTZO4T7IQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WH7U2LCA7KPPY7A5HGTZO4T7IQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/action/storage_attestation","attest_author":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/action/author_attestation","sign_citation":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/action/citation_signature","submit_replication":"https://pith.science/pith/WH7U2LCA7KPPY7A5HGTZO4T7IQ/action/replication_record"}},"created_at":"2026-07-05T02:29:57.078489+00:00","updated_at":"2026-07-05T02:29:57.078489+00:00"}