{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HWYA4NPJETPL7CW6EY5MJC5NNY","short_pith_number":"pith:HWYA4NPJ","schema_version":"1.0","canonical_sha256":"3db00e35e924debf8ade263ac48bad6e04eec20dcfd71c711b46f9574dabf5e5","source":{"kind":"arxiv","id":"2309.16482","version":2},"attestation_state":"computed","paper":{"title":"Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Boeddeker, Marc Delcroix, Reinhold Haeb-Umbach, Thilo von Neumann, Tobias Cord-Landwehr","submitted_at":"2023-09-28T14:45:46Z","abstract_excerpt":"We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuous Speech Separation (CSS) system with a TF-GridNet separation architecture, followed by a speaker-agnostic speech recognizer, we achieve state-of-the-art recognition performance in terms of Optimal Reference Combination Word Error Rate (ORC WER). Then, a d-vector-based diarization module is employed to extract speaker embeddings from the enhanced signals and to assign the CSS outputs to the correct speaker. Here, we"},"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":"2309.16482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-28T14:45:46Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"27fc29ef127e3404743fa90b30c3b0da818c45791388fd227dd89c50ecefb24f","abstract_canon_sha256":"45e9ae9c2b25fa7877723e131cdf91ac4ea843244675f416fbd1e9b444ef1954"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:39.751384Z","signature_b64":"w7LPxmMm8TvtkjXAbMmuAIOhpdNsA596smWsu7bRZcfOfyz1rni9aVDY+xVJcKbW+VL21mztuzPjzwlX7cgaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3db00e35e924debf8ade263ac48bad6e04eec20dcfd71c711b46f9574dabf5e5","last_reissued_at":"2026-07-05T08:15:39.750871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:39.750871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meeting Recognition with Continuous Speech Separation and Transcription-Supported Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Boeddeker, Marc Delcroix, Reinhold Haeb-Umbach, Thilo von Neumann, Tobias Cord-Landwehr","submitted_at":"2023-09-28T14:45:46Z","abstract_excerpt":"We propose a modular pipeline for the single-channel separation, recognition, and diarization of meeting-style recordings and evaluate it on the Libri-CSS dataset. Using a Continuous Speech Separation (CSS) system with a TF-GridNet separation architecture, followed by a speaker-agnostic speech recognizer, we achieve state-of-the-art recognition performance in terms of Optimal Reference Combination Word Error Rate (ORC WER). Then, a d-vector-based diarization module is employed to extract speaker embeddings from the enhanced signals and to assign the CSS outputs to the correct speaker. Here, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16482","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/2309.16482/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":"2309.16482","created_at":"2026-07-05T08:15:39.750925+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16482v2","created_at":"2026-07-05T08:15:39.750925+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16482","created_at":"2026-07-05T08:15:39.750925+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWYA4NPJETPL","created_at":"2026-07-05T08:15:39.750925+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWYA4NPJETPL7CW6","created_at":"2026-07-05T08:15:39.750925+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWYA4NPJ","created_at":"2026-07-05T08:15:39.750925+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08208","citing_title":"Diarization-Guided Qwen-ASR Adaptation for Multilingual Two-Speaker Conversational Speech","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY","json":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY.json","graph_json":"https://pith.science/api/pith-number/HWYA4NPJETPL7CW6EY5MJC5NNY/graph.json","events_json":"https://pith.science/api/pith-number/HWYA4NPJETPL7CW6EY5MJC5NNY/events.json","paper":"https://pith.science/paper/HWYA4NPJ"},"agent_actions":{"view_html":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY","download_json":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY.json","view_paper":"https://pith.science/paper/HWYA4NPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16482&json=true","fetch_graph":"https://pith.science/api/pith-number/HWYA4NPJETPL7CW6EY5MJC5NNY/graph.json","fetch_events":"https://pith.science/api/pith-number/HWYA4NPJETPL7CW6EY5MJC5NNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY/action/storage_attestation","attest_author":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY/action/author_attestation","sign_citation":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY/action/citation_signature","submit_replication":"https://pith.science/pith/HWYA4NPJETPL7CW6EY5MJC5NNY/action/replication_record"}},"created_at":"2026-07-05T08:15:39.750925+00:00","updated_at":"2026-07-05T08:15:39.750925+00:00"}