{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VLQYH3XA2O3JBNIKGVAI7G53KV","short_pith_number":"pith:VLQYH3XA","canonical_record":{"source":{"id":"2107.02852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-06T19:36:48Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"060a6393fb12dc2f5c76d3491edb50398d14f701e82ead37038b8f686d4ae2ed","abstract_canon_sha256":"e2a01bb7a6d3e4e1bbb5a91e8c99743284b8455d13420451395285cbe2ede975"},"schema_version":"1.0"},"canonical_sha256":"aae183eee0d3b690b50a35408f9bbb55777fd59ebd0ed02704673c1199820f1e","source":{"kind":"arxiv","id":"2107.02852","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02852","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02852v2","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02852","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"pith_short_12","alias_value":"VLQYH3XA2O3J","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"pith_short_16","alias_value":"VLQYH3XA2O3JBNIK","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"pith_short_8","alias_value":"VLQYH3XA","created_at":"2026-07-05T03:15:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VLQYH3XA2O3JBNIKGVAI7G53KV","target":"record","payload":{"canonical_record":{"source":{"id":"2107.02852","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-06T19:36:48Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"060a6393fb12dc2f5c76d3491edb50398d14f701e82ead37038b8f686d4ae2ed","abstract_canon_sha256":"e2a01bb7a6d3e4e1bbb5a91e8c99743284b8455d13420451395285cbe2ede975"},"schema_version":"1.0"},"canonical_sha256":"aae183eee0d3b690b50a35408f9bbb55777fd59ebd0ed02704673c1199820f1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:35.273682Z","signature_b64":"9YjDFQhMg5zqng4XQTVFaSkcfKBJ2jq/AUe7B22NSU/kiRWmccT7L+8OFNp5qYL89e/8elcdDLNfuXlnEzgFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aae183eee0d3b690b50a35408f9bbb55777fd59ebd0ed02704673c1199820f1e","last_reissued_at":"2026-07-05T03:15:35.273294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:35.273294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.02852","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7MrlioG7ljKJFX0G4YDY066A2u9vzlEofrGDmm/+Rseixl99FvZg7I/kWiQ2n7J3m4VXynQ+hW9qfEvmCM+aCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:46:55.158597Z"},"content_sha256":"dcd2b95de23dc962946d11948b783cd54f29c0c7a2d0694766c181d20fa9593f","schema_version":"1.0","event_id":"sha256:dcd2b95de23dc962946d11948b783cd54f29c0c7a2d0694766c181d20fa9593f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VLQYH3XA2O3JBNIKGVAI7G53KV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Naoyuki Kanda, Takuya Yoshioka, Tianyan Zhou, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Zhong Meng, Zhuo Chen","submitted_at":"2021-07-06T19:36:48Z","abstract_excerpt":"Speaker-attributed automatic speech recognition (SA-ASR) is a task to recognize \"who spoke what\" from multi-talker recordings. An SA-ASR system usually consists of multiple modules such as speech separation, speaker diarization and ASR. On the other hand, considering the joint optimization, an end-to-end (E2E) SA-ASR model has recently been proposed with promising results on simulation data. In this paper, we present our recent study on the comparison of such modular and joint approaches towards SA-ASR on real monaural recordings. We develop state-of-the-art SA-ASR systems for both modular and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02852","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/2107.02852/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ka/wSVm4mvkG3wR5PrAo5CpK3/yWOyY514E9pJQTQxeww6fUugqWo2XQ+2C11HwB1noaZ0B57O3PFQpONVF3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:46:55.158980Z"},"content_sha256":"f8bc4e6933dcfd13473afb6bf0e49a5145699977178d297e4710f5f0a0db584a","schema_version":"1.0","event_id":"sha256:f8bc4e6933dcfd13473afb6bf0e49a5145699977178d297e4710f5f0a0db584a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLQYH3XA2O3JBNIKGVAI7G53KV/bundle.json","state_url":"https://pith.science/pith/VLQYH3XA2O3JBNIKGVAI7G53KV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLQYH3XA2O3JBNIKGVAI7G53KV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T20:46:55Z","links":{"resolver":"https://pith.science/pith/VLQYH3XA2O3JBNIKGVAI7G53KV","bundle":"https://pith.science/pith/VLQYH3XA2O3JBNIKGVAI7G53KV/bundle.json","state":"https://pith.science/pith/VLQYH3XA2O3JBNIKGVAI7G53KV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLQYH3XA2O3JBNIKGVAI7G53KV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VLQYH3XA2O3JBNIKGVAI7G53KV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2a01bb7a6d3e4e1bbb5a91e8c99743284b8455d13420451395285cbe2ede975","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-06T19:36:48Z","title_canon_sha256":"060a6393fb12dc2f5c76d3491edb50398d14f701e82ead37038b8f686d4ae2ed"},"schema_version":"1.0","source":{"id":"2107.02852","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.02852","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"arxiv_version","alias_value":"2107.02852v2","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.02852","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"pith_short_12","alias_value":"VLQYH3XA2O3J","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"pith_short_16","alias_value":"VLQYH3XA2O3JBNIK","created_at":"2026-07-05T03:15:35Z"},{"alias_kind":"pith_short_8","alias_value":"VLQYH3XA","created_at":"2026-07-05T03:15:35Z"}],"graph_snapshots":[{"event_id":"sha256:f8bc4e6933dcfd13473afb6bf0e49a5145699977178d297e4710f5f0a0db584a","target":"graph","created_at":"2026-07-05T03:15:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.02852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speaker-attributed automatic speech recognition (SA-ASR) is a task to recognize \"who spoke what\" from multi-talker recordings. An SA-ASR system usually consists of multiple modules such as speech separation, speaker diarization and ASR. On the other hand, considering the joint optimization, an end-to-end (E2E) SA-ASR model has recently been proposed with promising results on simulation data. In this paper, we present our recent study on the comparison of such modular and joint approaches towards SA-ASR on real monaural recordings. We develop state-of-the-art SA-ASR systems for both modular and","authors_text":"Jian Wu, Naoyuki Kanda, Takuya Yoshioka, Tianyan Zhou, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Zhong Meng, Zhuo Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-06T19:36:48Z","title":"A Comparative Study of Modular and Joint Approaches for Speaker-Attributed ASR on Monaural Long-Form Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.02852","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dcd2b95de23dc962946d11948b783cd54f29c0c7a2d0694766c181d20fa9593f","target":"record","created_at":"2026-07-05T03:15:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2a01bb7a6d3e4e1bbb5a91e8c99743284b8455d13420451395285cbe2ede975","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-07-06T19:36:48Z","title_canon_sha256":"060a6393fb12dc2f5c76d3491edb50398d14f701e82ead37038b8f686d4ae2ed"},"schema_version":"1.0","source":{"id":"2107.02852","kind":"arxiv","version":2}},"canonical_sha256":"aae183eee0d3b690b50a35408f9bbb55777fd59ebd0ed02704673c1199820f1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aae183eee0d3b690b50a35408f9bbb55777fd59ebd0ed02704673c1199820f1e","first_computed_at":"2026-07-05T03:15:35.273294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:35.273294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9YjDFQhMg5zqng4XQTVFaSkcfKBJ2jq/AUe7B22NSU/kiRWmccT7L+8OFNp5qYL89e/8elcdDLNfuXlnEzgFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:35.273682Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.02852","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcd2b95de23dc962946d11948b783cd54f29c0c7a2d0694766c181d20fa9593f","sha256:f8bc4e6933dcfd13473afb6bf0e49a5145699977178d297e4710f5f0a0db584a"],"state_sha256":"a6445ee8c3b2bc2127612bc8ba51eee618d58581f567cc39986cace5bac8834a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yebcJAIs7k5aKuPxf/BMFhmpDN1e1BAuCHPRH+ZNGfmeQoBmwlTNe+PyAAyY6Vw46N99Xa2g2Mq81hYw9BO0Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:46:55.161456Z","bundle_sha256":"1c81fbece705d5869d6d3fafcb5acb952f34f7c8a0660d1d98aae725b8943fd3"}}