{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26PQFEMMXECF5XU7BKMDQC63JX","short_pith_number":"pith:26PQFEMM","schema_version":"1.0","canonical_sha256":"d79f02918cb9045ede9f0a98380bdb4dc4cb217248ea6df656bb6215265966bb","source":{"kind":"arxiv","id":"2405.11078","version":1},"attestation_state":"computed","paper":{"title":"Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Sanjeev Khudanpur, Shinji Watanabe, Szu-Jui Chen, Vimal Manohar, Yusuke Fujita, Zhiqi Wang","submitted_at":"2024-05-17T20:20:41Z","abstract_excerpt":"This paper summarizes our acoustic modeling efforts in the Johns Hopkins University speech recognition system for the CHiME-5 challenge to recognize highly-overlapped dinner party speech recorded by multiple microphone arrays. We explore data augmentation approaches, neural network architectures, front-end speech dereverberation, beamforming and robust i-vector extraction with comparisons of our in-house implementations and publicly available tools. We finally achieved a word error rate of 69.4% on the development set, which is a 11.7% absolute improvement over the previous baseline of 81.1%, "},"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":"2405.11078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-05-17T20:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"40636324cfc12c7ef7eb0562f95e72bfb9a55a22d52ef6616ffc5e57eb7f9e65","abstract_canon_sha256":"40c15750e0656aaf36a1808bc70f831608499b569c97c15d64699a82ffa9ebe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:32.775538Z","signature_b64":"cK98/2jLNJBcevrguRKrejg+Z48/XgEczR7oAkcZ9hrQkmabX44/Vomyu2ZWIRx8E2OX0bLnAy5W0XAut9uxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79f02918cb9045ede9f0a98380bdb4dc4cb217248ea6df656bb6215265966bb","last_reissued_at":"2026-07-05T08:20:32.775045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:32.775045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Sanjeev Khudanpur, Shinji Watanabe, Szu-Jui Chen, Vimal Manohar, Yusuke Fujita, Zhiqi Wang","submitted_at":"2024-05-17T20:20:41Z","abstract_excerpt":"This paper summarizes our acoustic modeling efforts in the Johns Hopkins University speech recognition system for the CHiME-5 challenge to recognize highly-overlapped dinner party speech recorded by multiple microphone arrays. We explore data augmentation approaches, neural network architectures, front-end speech dereverberation, beamforming and robust i-vector extraction with comparisons of our in-house implementations and publicly available tools. We finally achieved a word error rate of 69.4% on the development set, which is a 11.7% absolute improvement over the previous baseline of 81.1%, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11078","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/2405.11078/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":"2405.11078","created_at":"2026-07-05T08:20:32.775110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11078v1","created_at":"2026-07-05T08:20:32.775110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11078","created_at":"2026-07-05T08:20:32.775110+00:00"},{"alias_kind":"pith_short_12","alias_value":"26PQFEMMXECF","created_at":"2026-07-05T08:20:32.775110+00:00"},{"alias_kind":"pith_short_16","alias_value":"26PQFEMMXECF5XU7","created_at":"2026-07-05T08:20:32.775110+00:00"},{"alias_kind":"pith_short_8","alias_value":"26PQFEMM","created_at":"2026-07-05T08:20:32.775110+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/26PQFEMMXECF5XU7BKMDQC63JX","json":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX.json","graph_json":"https://pith.science/api/pith-number/26PQFEMMXECF5XU7BKMDQC63JX/graph.json","events_json":"https://pith.science/api/pith-number/26PQFEMMXECF5XU7BKMDQC63JX/events.json","paper":"https://pith.science/paper/26PQFEMM"},"agent_actions":{"view_html":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX","download_json":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX.json","view_paper":"https://pith.science/paper/26PQFEMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11078&json=true","fetch_graph":"https://pith.science/api/pith-number/26PQFEMMXECF5XU7BKMDQC63JX/graph.json","fetch_events":"https://pith.science/api/pith-number/26PQFEMMXECF5XU7BKMDQC63JX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX/action/storage_attestation","attest_author":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX/action/author_attestation","sign_citation":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX/action/citation_signature","submit_replication":"https://pith.science/pith/26PQFEMMXECF5XU7BKMDQC63JX/action/replication_record"}},"created_at":"2026-07-05T08:20:32.775110+00:00","updated_at":"2026-07-05T08:20:32.775110+00:00"}