{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5ZLDG4HM4TQRFA7K6YPSYWWYGH","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":"333faf42a4094cacd2da0ba09b0c68fda6f7902b5f6aa0cd76173bc606a3bbc4","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T03:55:14Z","title_canon_sha256":"c38719d6f0b43c284815bdef76c692b29dd6386110a537614a13cf626e48c947"},"schema_version":"1.0","source":{"id":"2309.08131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08131","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08131v1","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08131","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_12","alias_value":"5ZLDG4HM4TQR","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_16","alias_value":"5ZLDG4HM4TQRFA7K","created_at":"2026-07-05T06:51:02Z"},{"alias_kind":"pith_short_8","alias_value":"5ZLDG4HM","created_at":"2026-07-05T06:51:02Z"}],"graph_snapshots":[{"event_id":"sha256:d8d35341a0539c3c81b4509d3397b3fc3f6bf49570b1c41fcea908d987247628","target":"graph","created_at":"2026-07-05T06:51:02Z","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/2309.08131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Token-level serialized output training (t-SOT) was recently proposed to address the challenge of streaming multi-talker automatic speech recognition (ASR). T-SOT effectively handles overlapped speech by representing multi-talker transcriptions as a single token stream with $\\langle \\text{cc}\\rangle$ symbols interspersed. However, the use of a naive neural transducer architecture significantly constrained its applicability for text-only adaptation. To overcome this limitation, we propose a novel t-SOT model structure that incorporates the idea of factorized neural transducers (FNT). The propose","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Rui Zhao, Takuya Yoshioka, Zhuo Chen","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T03:55:14Z","title":"t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08131","kind":"arxiv","version":1},"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:e0f63420d745344a4eb7920ddf84dd029ca45f57902782a3f22d82e0bbf2322d","target":"record","created_at":"2026-07-05T06:51:02Z","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":"333faf42a4094cacd2da0ba09b0c68fda6f7902b5f6aa0cd76173bc606a3bbc4","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T03:55:14Z","title_canon_sha256":"c38719d6f0b43c284815bdef76c692b29dd6386110a537614a13cf626e48c947"},"schema_version":"1.0","source":{"id":"2309.08131","kind":"arxiv","version":1}},"canonical_sha256":"ee563370ece4e11283eaf61f2c5ad831e196da02945ca9e0443f64949aeef2b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee563370ece4e11283eaf61f2c5ad831e196da02945ca9e0443f64949aeef2b6","first_computed_at":"2026-07-05T06:51:02.424474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:02.424474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"02qJAou4KMRBAbgCBk6YRsx2faU7RdwWwjjL79uguYfAi5+Bx/S4C8jcUpnHfxou+IkYjmZhWR4LBYJEGMN6BA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:02.424877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0f63420d745344a4eb7920ddf84dd029ca45f57902782a3f22d82e0bbf2322d","sha256:d8d35341a0539c3c81b4509d3397b3fc3f6bf49570b1c41fcea908d987247628"],"state_sha256":"ae6c803b525715dc66cabd5254b832418b36c35bc5065680bd618cf47c593202"}