{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YMGH2UD6HOVGP5RDD6S3HFBK7U","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":"2674d58b5e7b1977d8e9ef1cc90ad2facc6107b3ac58ef6e90698e94f0391b09","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-30T19:24:57Z","title_canon_sha256":"1e15052953c3fcd0b694bdfe87683faea067a5911edf5df6facd62aa319a1af3"},"schema_version":"1.0","source":{"id":"2111.00316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00316","created_at":"2026-07-05T03:27:41Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00316v1","created_at":"2026-07-05T03:27:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00316","created_at":"2026-07-05T03:27:41Z"},{"alias_kind":"pith_short_12","alias_value":"YMGH2UD6HOVG","created_at":"2026-07-05T03:27:41Z"},{"alias_kind":"pith_short_16","alias_value":"YMGH2UD6HOVGP5RD","created_at":"2026-07-05T03:27:41Z"},{"alias_kind":"pith_short_8","alias_value":"YMGH2UD6","created_at":"2026-07-05T03:27:41Z"}],"graph_snapshots":[{"event_id":"sha256:83b4675f260f64ca03d1beae38ff26d004a0f99011a048be23466d4a68c6b93e","target":"graph","created_at":"2026-07-05T03:27:41Z","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/2111.00316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most current speech technology systems are designed to operate well even in the presence of multiple active speakers. However, most solutions assume that the number of co-current speakers is known. Unfortunately, this information might not always be available in real-world applications. In this study, we propose a real-time, single-channel attention-guided Convolutional Neural Network (CNN) to estimate the number of active speakers in overlapping speech. The proposed system extracts higher-level information from the speech spectral content using a CNN model. Next, the attention mechanism summa","authors_text":"John H.L. Hansen, Midia Yousefi","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-30T19:24:57Z","title":"Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00316","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:af8cfb4bf8e9218167d7ea2b4336ec2d29807a148202a0f72f1432786c0d7767","target":"record","created_at":"2026-07-05T03:27:41Z","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":"2674d58b5e7b1977d8e9ef1cc90ad2facc6107b3ac58ef6e90698e94f0391b09","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-30T19:24:57Z","title_canon_sha256":"1e15052953c3fcd0b694bdfe87683faea067a5911edf5df6facd62aa319a1af3"},"schema_version":"1.0","source":{"id":"2111.00316","kind":"arxiv","version":1}},"canonical_sha256":"c30c7d507e3baa67f6231fa5b3942afd03909b9ce3d790c1db789810608da687","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c30c7d507e3baa67f6231fa5b3942afd03909b9ce3d790c1db789810608da687","first_computed_at":"2026-07-05T03:27:41.194296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:41.194296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bjuyMleDmZ7C5zuVBIXVQTTVOTdKY3eZ3kwNs7wto+pO4XRLvaE3H50c9da6py4GnoX//qwbtmxqrpf43aBSBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:41.194794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af8cfb4bf8e9218167d7ea2b4336ec2d29807a148202a0f72f1432786c0d7767","sha256:83b4675f260f64ca03d1beae38ff26d004a0f99011a048be23466d4a68c6b93e"],"state_sha256":"9815f6c407e8a8c56b906715d5c5406eb424d4926b394e40663ed9c1d239f242"}