{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FFVHWMJRM2WP7KUZYWY6SDDIZA","short_pith_number":"pith:FFVHWMJR","schema_version":"1.0","canonical_sha256":"296a7b313166acffaa99c5b1e90c68c82e86fe18d85e2c0ddabd421d7622e4ba","source":{"kind":"arxiv","id":"2403.06570","version":2},"attestation_state":"computed","paper":{"title":"Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Cui (MULTISPEECH), Emmanuel Vincent (MULTISPEECH), Imran Ahamad Sheikh, Mostafa Sadeghi (MULTISPEECH)","submitted_at":"2024-03-11T10:11:29Z","abstract_excerpt":"Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in real-life scenarios, such as the AMI meeting corpus, for improved speaker assignment of speech segments. First, we propose a pipeline tailored to real-life applications involving Voice Activity Detection (VAD), Speaker Diarization (SD), and SA-ASR. Second, we advocate using VAD output segments to fine-tune the SA-ASR model, considering that it is also appli"},"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":"2403.06570","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T10:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"67a149d506f7611353fc5f8f4e2c4530bce319ca6651f16a9d27e9cfc9735cb3","abstract_canon_sha256":"42ab7b5f604226cc05df6784dc5d460206cdbe1c71688e22f3114de219b54b5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:18.962274Z","signature_b64":"7Zu1Pch2Yi8BJ56N6iJTwynY/lyx4eAw7gdoxhyzNUBmJ8I1qzolCYEVD9v9FSnTcZ0JAHbNjpGB4l7W3wFGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296a7b313166acffaa99c5b1e90c68c82e86fe18d85e2c0ddabd421d7622e4ba","last_reissued_at":"2026-07-05T09:03:18.961743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:18.961743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Cui (MULTISPEECH), Emmanuel Vincent (MULTISPEECH), Imran Ahamad Sheikh, Mostafa Sadeghi (MULTISPEECH)","submitted_at":"2024-03-11T10:11:29Z","abstract_excerpt":"Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in real-life scenarios, such as the AMI meeting corpus, for improved speaker assignment of speech segments. First, we propose a pipeline tailored to real-life applications involving Voice Activity Detection (VAD), Speaker Diarization (SD), and SA-ASR. Second, we advocate using VAD output segments to fine-tune the SA-ASR model, considering that it is also appli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06570","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/2403.06570/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":"2403.06570","created_at":"2026-07-05T09:03:18.961807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06570v2","created_at":"2026-07-05T09:03:18.961807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06570","created_at":"2026-07-05T09:03:18.961807+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFVHWMJRM2WP","created_at":"2026-07-05T09:03:18.961807+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFVHWMJRM2WP7KUZ","created_at":"2026-07-05T09:03:18.961807+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFVHWMJR","created_at":"2026-07-05T09:03:18.961807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.19875","citing_title":"Speaker Embeddings to Improve Tracking of Intermittent and Moving Speakers","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA","json":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA.json","graph_json":"https://pith.science/api/pith-number/FFVHWMJRM2WP7KUZYWY6SDDIZA/graph.json","events_json":"https://pith.science/api/pith-number/FFVHWMJRM2WP7KUZYWY6SDDIZA/events.json","paper":"https://pith.science/paper/FFVHWMJR"},"agent_actions":{"view_html":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA","download_json":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA.json","view_paper":"https://pith.science/paper/FFVHWMJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06570&json=true","fetch_graph":"https://pith.science/api/pith-number/FFVHWMJRM2WP7KUZYWY6SDDIZA/graph.json","fetch_events":"https://pith.science/api/pith-number/FFVHWMJRM2WP7KUZYWY6SDDIZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA/action/storage_attestation","attest_author":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA/action/author_attestation","sign_citation":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA/action/citation_signature","submit_replication":"https://pith.science/pith/FFVHWMJRM2WP7KUZYWY6SDDIZA/action/replication_record"}},"created_at":"2026-07-05T09:03:18.961807+00:00","updated_at":"2026-07-05T09:03:18.961807+00:00"}