{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YMGH2UD6HOVGP5RDD6S3HFBK7U","short_pith_number":"pith:YMGH2UD6","schema_version":"1.0","canonical_sha256":"c30c7d507e3baa67f6231fa5b3942afd03909b9ce3d790c1db789810608da687","source":{"kind":"arxiv","id":"2111.00316","version":1},"attestation_state":"computed","paper":{"title":"Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"John H.L. Hansen, Midia Yousefi","submitted_at":"2021-10-30T19:24:57Z","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"},"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":"2111.00316","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-10-30T19:24:57Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"1e15052953c3fcd0b694bdfe87683faea067a5911edf5df6facd62aa319a1af3","abstract_canon_sha256":"2674d58b5e7b1977d8e9ef1cc90ad2facc6107b3ac58ef6e90698e94f0391b09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:41.194794Z","signature_b64":"bjuyMleDmZ7C5zuVBIXVQTTVOTdKY3eZ3kwNs7wto+pO4XRLvaE3H50c9da6py4GnoX//qwbtmxqrpf43aBSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c30c7d507e3baa67f6231fa5b3942afd03909b9ce3d790c1db789810608da687","last_reissued_at":"2026-07-05T03:27:41.194296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:41.194296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"John H.L. Hansen, Midia Yousefi","submitted_at":"2021-10-30T19:24:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00316","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/2111.00316/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":"2111.00316","created_at":"2026-07-05T03:27:41.194426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00316v1","created_at":"2026-07-05T03:27:41.194426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00316","created_at":"2026-07-05T03:27:41.194426+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMGH2UD6HOVG","created_at":"2026-07-05T03:27:41.194426+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMGH2UD6HOVGP5RD","created_at":"2026-07-05T03:27:41.194426+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMGH2UD6","created_at":"2026-07-05T03:27:41.194426+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/YMGH2UD6HOVGP5RDD6S3HFBK7U","json":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U.json","graph_json":"https://pith.science/api/pith-number/YMGH2UD6HOVGP5RDD6S3HFBK7U/graph.json","events_json":"https://pith.science/api/pith-number/YMGH2UD6HOVGP5RDD6S3HFBK7U/events.json","paper":"https://pith.science/paper/YMGH2UD6"},"agent_actions":{"view_html":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U","download_json":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U.json","view_paper":"https://pith.science/paper/YMGH2UD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00316&json=true","fetch_graph":"https://pith.science/api/pith-number/YMGH2UD6HOVGP5RDD6S3HFBK7U/graph.json","fetch_events":"https://pith.science/api/pith-number/YMGH2UD6HOVGP5RDD6S3HFBK7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U/action/storage_attestation","attest_author":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U/action/author_attestation","sign_citation":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U/action/citation_signature","submit_replication":"https://pith.science/pith/YMGH2UD6HOVGP5RDD6S3HFBK7U/action/replication_record"}},"created_at":"2026-07-05T03:27:41.194426+00:00","updated_at":"2026-07-05T03:27:41.194426+00:00"}