{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q7FP3C5PMN6KL7K4QAF6CNQ37G","short_pith_number":"pith:Q7FP3C5P","schema_version":"1.0","canonical_sha256":"87cafd8baf637ca5fd5c800be1361bf986002f167ead3e605e878c44b8aa11d2","source":{"kind":"arxiv","id":"2505.23207","version":1},"attestation_state":"computed","paper":{"title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Li Zhang, Pan Zhou, Qing Wang, Zhaokai Sun","submitted_at":"2025-05-29T07:47:48Z","abstract_excerpt":"Overlapping Speech Detection (OSD) aims to identify regions where multiple speakers overlap in a conversation, a critical challenge in multi-party speech processing. This work proposes a speaker-aware progressive OSD model that leverages a progressive training strategy to enhance the correlation between subtasks such as voice activity detection (VAD) and overlap detection. To improve acoustic representation, we explore the effectiveness of state-of-the-art self-supervised learning (SSL) models, including WavLM and wav2vec 2.0, while incorporating a speaker attention module to enrich features 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":"2505.23207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-29T07:47:48Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"95eaffd637d90a85fc0770b97760ce16207a6c09a5266b6c55460ffaf23d1a0e","abstract_canon_sha256":"27a6eaa3b40db1c272c9a140587d052ea2dad255171389d8ee9270756a557e3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:12.086751Z","signature_b64":"RRSCdTA8wBB3UL6WsIPINdtzPgpj/3xReIPtz4liTNf81yM0kSyMa1jQf5koCaau0LEK8D2Jbt6xUItgOsrACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87cafd8baf637ca5fd5c800be1361bf986002f167ead3e605e878c44b8aa11d2","last_reissued_at":"2026-07-05T11:12:12.086263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:12.086263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Robust Overlapping Speech Detection: A Speaker-Aware Progressive Approach Using WavLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Lei Xie, Li Zhang, Pan Zhou, Qing Wang, Zhaokai Sun","submitted_at":"2025-05-29T07:47:48Z","abstract_excerpt":"Overlapping Speech Detection (OSD) aims to identify regions where multiple speakers overlap in a conversation, a critical challenge in multi-party speech processing. This work proposes a speaker-aware progressive OSD model that leverages a progressive training strategy to enhance the correlation between subtasks such as voice activity detection (VAD) and overlap detection. To improve acoustic representation, we explore the effectiveness of state-of-the-art self-supervised learning (SSL) models, including WavLM and wav2vec 2.0, while incorporating a speaker attention module to enrich features w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23207","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/2505.23207/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":"2505.23207","created_at":"2026-07-05T11:12:12.086324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23207v1","created_at":"2026-07-05T11:12:12.086324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23207","created_at":"2026-07-05T11:12:12.086324+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7FP3C5PMN6K","created_at":"2026-07-05T11:12:12.086324+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7FP3C5PMN6KL7K4","created_at":"2026-07-05T11:12:12.086324+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7FP3C5P","created_at":"2026-07-05T11:12:12.086324+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":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G","json":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G.json","graph_json":"https://pith.science/api/pith-number/Q7FP3C5PMN6KL7K4QAF6CNQ37G/graph.json","events_json":"https://pith.science/api/pith-number/Q7FP3C5PMN6KL7K4QAF6CNQ37G/events.json","paper":"https://pith.science/paper/Q7FP3C5P"},"agent_actions":{"view_html":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G","download_json":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G.json","view_paper":"https://pith.science/paper/Q7FP3C5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23207&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7FP3C5PMN6KL7K4QAF6CNQ37G/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7FP3C5PMN6KL7K4QAF6CNQ37G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G/action/storage_attestation","attest_author":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G/action/author_attestation","sign_citation":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G/action/citation_signature","submit_replication":"https://pith.science/pith/Q7FP3C5PMN6KL7K4QAF6CNQ37G/action/replication_record"}},"created_at":"2026-07-05T11:12:12.086324+00:00","updated_at":"2026-07-05T11:12:12.086324+00:00"}