{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XOYGMP2Q5H67P2DUXDL43VTIKO","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":"2890b9f7470696df83f22cefb6ba94f4918021dd78dc31bcbee6ccb17fc38693","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-09-17T13:57:52Z","title_canon_sha256":"8f64cdd2d127b0fad7dd062b2923549d8078b215c8fb31798cb6650a669151d0"},"schema_version":"1.0","source":{"id":"2109.08555","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.08555","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"arxiv_version","alias_value":"2109.08555v2","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08555","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"pith_short_12","alias_value":"XOYGMP2Q5H67","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"pith_short_16","alias_value":"XOYGMP2Q5H67P2DU","created_at":"2026-07-05T03:50:36Z"},{"alias_kind":"pith_short_8","alias_value":"XOYGMP2Q","created_at":"2026-07-05T03:50:36Z"}],"graph_snapshots":[{"event_id":"sha256:5f9b4e28fb100f301c232e1eb57f6b13fa2a5794d92c20ccf11e3980f3e6a6b9","target":"graph","created_at":"2026-07-05T03:50:36Z","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/2109.08555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and Recognition Transducer (SURT) model, and show that naively extending the single-turn model to this harder setting incurs a performance penalty. As a solution, we propose the dual-path (DP) modeling strategy first used for time-domain speech separation. We experiment with LSTM and Transformer based DP models, and show that they improve word error rate (WER) per","authors_text":"Desh Raj, Jinyu Li, Liang Lu, Yashesh Gaur, Zhuo Chen","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-09-17T13:57:52Z","title":"Continuous Streaming Multi-Talker ASR with Dual-path Transducers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08555","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:c0e9e088c63fac5881314743ba083d4e3bc63020ee86b9d74e4575aae6bf314b","target":"record","created_at":"2026-07-05T03:50:36Z","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":"2890b9f7470696df83f22cefb6ba94f4918021dd78dc31bcbee6ccb17fc38693","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-09-17T13:57:52Z","title_canon_sha256":"8f64cdd2d127b0fad7dd062b2923549d8078b215c8fb31798cb6650a669151d0"},"schema_version":"1.0","source":{"id":"2109.08555","kind":"arxiv","version":2}},"canonical_sha256":"bbb0663f50e9fdf7e874b8d7cdd668538567e34e1df2ae53764f5bdfca8332df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbb0663f50e9fdf7e874b8d7cdd668538567e34e1df2ae53764f5bdfca8332df","first_computed_at":"2026-07-05T03:50:36.436894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:50:36.436894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PQoH1iUBsmllQilYgrxD89pHIcoopfrvDUuu44spqK5pX9jDucdpUjmJXCS3BDwet3p3M4fmtTGvK8AY6NqKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:50:36.437450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.08555","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0e9e088c63fac5881314743ba083d4e3bc63020ee86b9d74e4575aae6bf314b","sha256:5f9b4e28fb100f301c232e1eb57f6b13fa2a5794d92c20ccf11e3980f3e6a6b9"],"state_sha256":"24e7b7daa85d7fe9c744ae738ca67663550dabd4f72f911904fc8c2e946c374f"}