{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BV75GKRG7VQAIIUUHGZ5A3VLAW","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":"03a400a1cd4de24be389224c1eee4c74c3b050fed100e171ff46d2593e1c6db0","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T21:42:00Z","title_canon_sha256":"2cf3a09400b63521f21b1aef65a0ad020624f4e1b8927144b3348b58a6c59fa4"},"schema_version":"1.0","source":{"id":"2203.16685","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.16685","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"2203.16685v2","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16685","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"BV75GKRG7VQA","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"BV75GKRG7VQAIIUU","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"BV75GKRG","created_at":"2026-07-05T04:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:57198ff6edce86c4fe7e23c2b3e23fb480559f7b4c236faaeac45770b1259b2f","target":"graph","created_at":"2026-07-05T04:40:26Z","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/2203.16685/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize ``who spoke what'' with low latency even when multiple people are speaking simultaneously. Our model is based on token-level serialized output training (t-SOT) which was recently proposed to transcribe multi-talker speech in a streaming fashion. To further recognize speaker identities, we propose an encoder-decoder based speaker embedding extractor that can estimate a speaker representation for each recognized token not only from non-overlapping speech but also from overlapping spe","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Xiong Xiao, Yashesh Gaur, Yu Wu, 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":"2022-03-30T21:42:00Z","title":"Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16685","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":"sha256:707047b481cf1dcf77adfa7a11117c565610b6c234fb36c57d4101dcb80db20f","target":"record","created_at":"2026-07-05T04:40:26Z","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":"03a400a1cd4de24be389224c1eee4c74c3b050fed100e171ff46d2593e1c6db0","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-03-30T21:42:00Z","title_canon_sha256":"2cf3a09400b63521f21b1aef65a0ad020624f4e1b8927144b3348b58a6c59fa4"},"schema_version":"1.0","source":{"id":"2203.16685","kind":"arxiv","version":2}},"canonical_sha256":"0d7fd32a26fd6004229439b3d06eab059a31632e0fca3621a4ec197860a2f71f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d7fd32a26fd6004229439b3d06eab059a31632e0fca3621a4ec197860a2f71f","first_computed_at":"2026-07-05T04:40:26.669473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:26.669473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xzc05p6jp9i2F7ewYT2efd+T97k5hOBY0aXPW84hMSTRWf17+OwiqXQbKImZRzeS/Ismy5kWUoP32YO6glnnDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:26.670005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.16685","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:707047b481cf1dcf77adfa7a11117c565610b6c234fb36c57d4101dcb80db20f","sha256:57198ff6edce86c4fe7e23c2b3e23fb480559f7b4c236faaeac45770b1259b2f"],"state_sha256":"5d4a5ce8cff2807c5bee6c8d08ef72e334804f294551a3e709f3215c59b28515"}