{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:TDWIXFGOQ7RWMVUDIA4EBYY2TY","short_pith_number":"pith:TDWIXFGO","schema_version":"1.0","canonical_sha256":"98ec8b94ce87e3665683403840e31a9e372c9278aca346441b74b99c6c44a2ea","source":{"kind":"arxiv","id":"2011.02921","version":1},"attestation_state":"computed","paper":{"title":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Liang Lu, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Yashesh Gaur, Zhong Meng, Zhuo Chen","submitted_at":"2020-11-03T22:28:57Z","abstract_excerpt":"Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous study, the model parameters were trained based on the speaker-attributed maximum mutual information (SA-MMI) criterion, with which the joint posterior probability for multi-talker transcription and speaker identification are maximized over training data. Although SA-MMI training showed promising results for overlapped speech consisting of various numbers of spea"},"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":"2011.02921","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-11-03T22:28:57Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"988a2602ea258a229b26d110107d8bb0e4f06ce7ae9ae5e361832fb3e43f3bd6","abstract_canon_sha256":"933f9c38a854f92d603059eed9a139112ffc50f36eb5aa3e0fbdaac227a91f16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:27.333791Z","signature_b64":"xQoEmMIkbSQgN70Ss5aqhTJ7lRrN+1RnVNJWDv7s86bS5bft4MNHXxgKToAwjF87x5PHETWvR3XipJZX1KTZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98ec8b94ce87e3665683403840e31a9e372c9278aca346441b74b99c6c44a2ea","last_reissued_at":"2026-07-05T01:49:27.333353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:27.333353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Minimum Bayes Risk Training for End-to-End Speaker-Attributed ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Liang Lu, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Yashesh Gaur, Zhong Meng, Zhuo Chen","submitted_at":"2020-11-03T22:28:57Z","abstract_excerpt":"Recently, an end-to-end speaker-attributed automatic speech recognition (E2E SA-ASR) model was proposed as a joint model of speaker counting, speech recognition and speaker identification for monaural overlapped speech. In the previous study, the model parameters were trained based on the speaker-attributed maximum mutual information (SA-MMI) criterion, with which the joint posterior probability for multi-talker transcription and speaker identification are maximized over training data. Although SA-MMI training showed promising results for overlapped speech consisting of various numbers of spea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02921","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/2011.02921/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":"2011.02921","created_at":"2026-07-05T01:49:27.333418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02921v1","created_at":"2026-07-05T01:49:27.333418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02921","created_at":"2026-07-05T01:49:27.333418+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDWIXFGOQ7RW","created_at":"2026-07-05T01:49:27.333418+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDWIXFGOQ7RWMVUD","created_at":"2026-07-05T01:49:27.333418+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDWIXFGO","created_at":"2026-07-05T01:49:27.333418+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/TDWIXFGOQ7RWMVUDIA4EBYY2TY","json":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY.json","graph_json":"https://pith.science/api/pith-number/TDWIXFGOQ7RWMVUDIA4EBYY2TY/graph.json","events_json":"https://pith.science/api/pith-number/TDWIXFGOQ7RWMVUDIA4EBYY2TY/events.json","paper":"https://pith.science/paper/TDWIXFGO"},"agent_actions":{"view_html":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY","download_json":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY.json","view_paper":"https://pith.science/paper/TDWIXFGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02921&json=true","fetch_graph":"https://pith.science/api/pith-number/TDWIXFGOQ7RWMVUDIA4EBYY2TY/graph.json","fetch_events":"https://pith.science/api/pith-number/TDWIXFGOQ7RWMVUDIA4EBYY2TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY/action/storage_attestation","attest_author":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY/action/author_attestation","sign_citation":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY/action/citation_signature","submit_replication":"https://pith.science/pith/TDWIXFGOQ7RWMVUDIA4EBYY2TY/action/replication_record"}},"created_at":"2026-07-05T01:49:27.333418+00:00","updated_at":"2026-07-05T01:49:27.333418+00:00"}