{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AK4366YVPV6PYAUINO4CTZZMB4","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":"55a0c6136604e1424a45c156b17d39d4254258762613b1671e1b1bc5c168a294","cross_cats_sorted":["cs.AI","cs.NE","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-24T14:29:21Z","title_canon_sha256":"36e74d3815504703524a30e56b7038428df664bccf317cde10eaf5d0aad6d044"},"schema_version":"1.0","source":{"id":"2307.13012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13012","created_at":"2026-07-05T06:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13012v1","created_at":"2026-07-05T06:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13012","created_at":"2026-07-05T06:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"AK4366YVPV6P","created_at":"2026-07-05T06:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"AK4366YVPV6PYAUI","created_at":"2026-07-05T06:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"AK4366YV","created_at":"2026-07-05T06:34:07Z"}],"graph_snapshots":[{"event_id":"sha256:ff349af4f68c0137348f9bbe88d1ad3fa7390f077147286ec12122fb57cbdfa5","target":"graph","created_at":"2026-07-05T06:34:07Z","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/2307.13012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice activity and overlapped speech detection (respectively VAD and OSD) are key pre-processing tasks for speaker diarization. The final segmentation performance highly relies on the robustness of these sub-tasks. Recent studies have shown VAD and OSD can be trained jointly using a multi-class classification model. However, these works are often restricted to a specific speech domain, lacking information about the generalization capacities of the systems. This paper proposes a complete and new benchmark of different VAD and OSD models, on multiple audio setups (single/multi-channel) and speec","authors_text":"Anthony Larcher (LIUM), Antoine Laurent (LIUM), Jean-Hugh Thomas (LAUM), LAUM), Marie Tahon (LIUM), Martin Lebourdais (LIUM), Silvio Montresor (LAUM), Sylvain Meignier (LIUM), Th\\'eo Mariotte (LIUM","cross_cats":["cs.AI","cs.NE","eess.AS","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-24T14:29:21Z","title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13012","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:e00050856761d90d25aa670c8d202e49ae0b98262ddb462222f32a0c66d32a0b","target":"record","created_at":"2026-07-05T06:34:07Z","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":"55a0c6136604e1424a45c156b17d39d4254258762613b1671e1b1bc5c168a294","cross_cats_sorted":["cs.AI","cs.NE","eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-24T14:29:21Z","title_canon_sha256":"36e74d3815504703524a30e56b7038428df664bccf317cde10eaf5d0aad6d044"},"schema_version":"1.0","source":{"id":"2307.13012","kind":"arxiv","version":1}},"canonical_sha256":"02b9bf7b157d7cfc02886bb829e72c0f0b32c06265c5e0841c1b816cef4de12c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02b9bf7b157d7cfc02886bb829e72c0f0b32c06265c5e0841c1b816cef4de12c","first_computed_at":"2026-07-05T06:34:07.957800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:07.957800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmxHiEAO4bleSXfmsjbNDvqg6HtP6vD+21Uq0ygIoqcP0gM6ttxeY2/hpV/TlRKEjfIU6tQEaZVs3xpDY+0vCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:07.958274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.13012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00050856761d90d25aa670c8d202e49ae0b98262ddb462222f32a0c66d32a0b","sha256:ff349af4f68c0137348f9bbe88d1ad3fa7390f077147286ec12122fb57cbdfa5"],"state_sha256":"220cb75f2e1d3869a7a28fba55e0d9b9698e718f78a6c795641c29fbf9b585af"}