{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IE7LAGWMNYO5UDLALUQTPRGXWA","short_pith_number":"pith:IE7LAGWM","schema_version":"1.0","canonical_sha256":"413eb01acc6e1dda0d605d2137c4d7b03e7f8cc537e9348ab0677d2e6c4ce800","source":{"kind":"arxiv","id":"2210.15715","version":2},"attestation_state":"computed","paper":{"title":"Simulating realistic speech overlaps improves multi-talker ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Muqiao Yang, Naoyuki Kanda, Sunit Sivasankaran, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","submitted_at":"2022-10-27T18:29:39Z","abstract_excerpt":"Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a na\\\"ive simulation of multi-talker speech by randomly mixing multiple utterances was conventionally used for model training. In this work, we propose an improved technique to simulate multi-talker overlapping speech with realistic speech overlaps, where an arbitrary pattern of speech overlaps is represented by a sequence of discret"},"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":"2210.15715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-27T18:29:39Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"88f7b6d7692e9a91d2bc0f4b8497dd80968fd1972fd367381bfec59fb5bcfd9c","abstract_canon_sha256":"aaf07ab4574351d367556f378611994ad293788d290490be9437fc1cdda95b17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:13.086819Z","signature_b64":"B0vQucgSJKohSnxf64XJqv/mnoRTckzvyO52KP6xx981e/1Fh77xK792OaAoksIvHt6yAX67kAEEBI8q6VjNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"413eb01acc6e1dda0d605d2137c4d7b03e7f8cc537e9348ab0677d2e6c4ce800","last_reissued_at":"2026-07-05T05:17:13.086359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:13.086359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulating realistic speech overlaps improves multi-talker ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Muqiao Yang, Naoyuki Kanda, Sunit Sivasankaran, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","submitted_at":"2022-10-27T18:29:39Z","abstract_excerpt":"Multi-talker automatic speech recognition (ASR) has been studied to generate transcriptions of natural conversation including overlapping speech of multiple speakers. Due to the difficulty in acquiring real conversation data with high-quality human transcriptions, a na\\\"ive simulation of multi-talker speech by randomly mixing multiple utterances was conventionally used for model training. In this work, we propose an improved technique to simulate multi-talker overlapping speech with realistic speech overlaps, where an arbitrary pattern of speech overlaps is represented by a sequence of discret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15715","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/2210.15715/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":"2210.15715","created_at":"2026-07-05T05:17:13.086419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15715v2","created_at":"2026-07-05T05:17:13.086419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15715","created_at":"2026-07-05T05:17:13.086419+00:00"},{"alias_kind":"pith_short_12","alias_value":"IE7LAGWMNYO5","created_at":"2026-07-05T05:17:13.086419+00:00"},{"alias_kind":"pith_short_16","alias_value":"IE7LAGWMNYO5UDLA","created_at":"2026-07-05T05:17:13.086419+00:00"},{"alias_kind":"pith_short_8","alias_value":"IE7LAGWM","created_at":"2026-07-05T05:17:13.086419+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/IE7LAGWMNYO5UDLALUQTPRGXWA","json":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA.json","graph_json":"https://pith.science/api/pith-number/IE7LAGWMNYO5UDLALUQTPRGXWA/graph.json","events_json":"https://pith.science/api/pith-number/IE7LAGWMNYO5UDLALUQTPRGXWA/events.json","paper":"https://pith.science/paper/IE7LAGWM"},"agent_actions":{"view_html":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA","download_json":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA.json","view_paper":"https://pith.science/paper/IE7LAGWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15715&json=true","fetch_graph":"https://pith.science/api/pith-number/IE7LAGWMNYO5UDLALUQTPRGXWA/graph.json","fetch_events":"https://pith.science/api/pith-number/IE7LAGWMNYO5UDLALUQTPRGXWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA/action/storage_attestation","attest_author":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA/action/author_attestation","sign_citation":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA/action/citation_signature","submit_replication":"https://pith.science/pith/IE7LAGWMNYO5UDLALUQTPRGXWA/action/replication_record"}},"created_at":"2026-07-05T05:17:13.086419+00:00","updated_at":"2026-07-05T05:17:13.086419+00:00"}