{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AK4366YVPV6PYAUINO4CTZZMB4","short_pith_number":"pith:AK4366YV","schema_version":"1.0","canonical_sha256":"02b9bf7b157d7cfc02886bb829e72c0f0b32c06265c5e0841c1b816cef4de12c","source":{"kind":"arxiv","id":"2307.13012","version":1},"attestation_state":"computed","paper":{"title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","eess.AS","eess.SP"],"primary_cat":"cs.SD","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","submitted_at":"2023-07-24T14:29:21Z","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"},"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":"2307.13012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-24T14:29:21Z","cross_cats_sorted":["cs.AI","cs.NE","eess.AS","eess.SP"],"title_canon_sha256":"36e74d3815504703524a30e56b7038428df664bccf317cde10eaf5d0aad6d044","abstract_canon_sha256":"55a0c6136604e1424a45c156b17d39d4254258762613b1671e1b1bc5c168a294"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:07.958274Z","signature_b64":"qmxHiEAO4bleSXfmsjbNDvqg6HtP6vD+21Uq0ygIoqcP0gM6ttxeY2/hpV/TlRKEjfIU6tQEaZVs3xpDY+0vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b9bf7b157d7cfc02886bb829e72c0f0b32c06265c5e0841c1b816cef4de12c","last_reissued_at":"2026-07-05T06:34:07.957800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:07.957800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","eess.AS","eess.SP"],"primary_cat":"cs.SD","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","submitted_at":"2023-07-24T14:29:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13012","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/2307.13012/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":"2307.13012","created_at":"2026-07-05T06:34:07.957854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13012v1","created_at":"2026-07-05T06:34:07.957854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13012","created_at":"2026-07-05T06:34:07.957854+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK4366YVPV6P","created_at":"2026-07-05T06:34:07.957854+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK4366YVPV6PYAUI","created_at":"2026-07-05T06:34:07.957854+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK4366YV","created_at":"2026-07-05T06:34:07.957854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23207","citing_title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4","json":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4.json","graph_json":"https://pith.science/api/pith-number/AK4366YVPV6PYAUINO4CTZZMB4/graph.json","events_json":"https://pith.science/api/pith-number/AK4366YVPV6PYAUINO4CTZZMB4/events.json","paper":"https://pith.science/paper/AK4366YV"},"agent_actions":{"view_html":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4","download_json":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4.json","view_paper":"https://pith.science/paper/AK4366YV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13012&json=true","fetch_graph":"https://pith.science/api/pith-number/AK4366YVPV6PYAUINO4CTZZMB4/graph.json","fetch_events":"https://pith.science/api/pith-number/AK4366YVPV6PYAUINO4CTZZMB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4/action/storage_attestation","attest_author":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4/action/author_attestation","sign_citation":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4/action/citation_signature","submit_replication":"https://pith.science/pith/AK4366YVPV6PYAUINO4CTZZMB4/action/replication_record"}},"created_at":"2026-07-05T06:34:07.957854+00:00","updated_at":"2026-07-05T06:34:07.957854+00:00"}