{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UHM4PO3Z6HGW3BNYRLQDRZFESH","short_pith_number":"pith:UHM4PO3Z","schema_version":"1.0","canonical_sha256":"a1d9c7bb79f1cd6d85b88ae038e4a491d259d2cbb6c386b26c0ebae11343e9ad","source":{"kind":"arxiv","id":"2212.05271","version":2},"attestation_state":"computed","paper":{"title":"GPU-accelerated Guided Source Separation for Meeting Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Desh Raj, Sanjeev Khudanpur","submitted_at":"2022-12-10T11:20:17Z","abstract_excerpt":"Guided source separation (GSS) is a type of target-speaker extraction method that relies on pre-computed speaker activities and blind source separation to perform front-end enhancement of overlapped speech signals. It was first proposed during the CHiME-5 challenge and provided significant improvements over the delay-and-sum beamforming baseline. Despite its strengths, however, the method has seen limited adoption for meeting transcription benchmarks primarily due to its high computation time. In this paper, we describe our improved implementation of GSS that leverages the power of modern GPU-"},"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":"2212.05271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-12-10T11:20:17Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d3b52ff8a79b656e9d24bc5f05ae2bcffa8147e01acb32011963adf41c9a3def","abstract_canon_sha256":"2a804d4130e4d5c80be1f58d476d9f8dc8c4fe3c1afec5a5fe26643a4bc42718"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:30.815325Z","signature_b64":"nuzajxsV/kN5TX/3zdQB0ZF5N8lqRH2qDVGbOkbFp3JSikY1pW+y9y1OYxHxmdNoY//yjesh3DeVBUix1+l6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d9c7bb79f1cd6d85b88ae038e4a491d259d2cbb6c386b26c0ebae11343e9ad","last_reissued_at":"2026-07-05T06:40:30.814796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:30.814796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPU-accelerated Guided Source Separation for Meeting Transcription","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Desh Raj, Sanjeev Khudanpur","submitted_at":"2022-12-10T11:20:17Z","abstract_excerpt":"Guided source separation (GSS) is a type of target-speaker extraction method that relies on pre-computed speaker activities and blind source separation to perform front-end enhancement of overlapped speech signals. It was first proposed during the CHiME-5 challenge and provided significant improvements over the delay-and-sum beamforming baseline. Despite its strengths, however, the method has seen limited adoption for meeting transcription benchmarks primarily due to its high computation time. In this paper, we describe our improved implementation of GSS that leverages the power of modern GPU-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.05271","kind":"arxiv","version":2},"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/2212.05271/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":"2212.05271","created_at":"2026-07-05T06:40:30.814857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.05271v2","created_at":"2026-07-05T06:40:30.814857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.05271","created_at":"2026-07-05T06:40:30.814857+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHM4PO3Z6HGW","created_at":"2026-07-05T06:40:30.814857+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHM4PO3Z6HGW3BNY","created_at":"2026-07-05T06:40:30.814857+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHM4PO3Z","created_at":"2026-07-05T06:40:30.814857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29497","citing_title":"Position-Aware Target Speaker Extraction for Long-Form Multi-Party Conversations: A Diarization-Free Framework for ASR","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH","json":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH.json","graph_json":"https://pith.science/api/pith-number/UHM4PO3Z6HGW3BNYRLQDRZFESH/graph.json","events_json":"https://pith.science/api/pith-number/UHM4PO3Z6HGW3BNYRLQDRZFESH/events.json","paper":"https://pith.science/paper/UHM4PO3Z"},"agent_actions":{"view_html":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH","download_json":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH.json","view_paper":"https://pith.science/paper/UHM4PO3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.05271&json=true","fetch_graph":"https://pith.science/api/pith-number/UHM4PO3Z6HGW3BNYRLQDRZFESH/graph.json","fetch_events":"https://pith.science/api/pith-number/UHM4PO3Z6HGW3BNYRLQDRZFESH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH/action/storage_attestation","attest_author":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH/action/author_attestation","sign_citation":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH/action/citation_signature","submit_replication":"https://pith.science/pith/UHM4PO3Z6HGW3BNYRLQDRZFESH/action/replication_record"}},"created_at":"2026-07-05T06:40:30.814857+00:00","updated_at":"2026-07-05T06:40:30.814857+00:00"}