{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5ZLDG4HM4TQRFA7K6YPSYWWYGH","short_pith_number":"pith:5ZLDG4HM","schema_version":"1.0","canonical_sha256":"ee563370ece4e11283eaf61f2c5ad831e196da02945ca9e0443f64949aeef2b6","source":{"kind":"arxiv","id":"2309.08131","version":1},"attestation_state":"computed","paper":{"title":"t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Rui Zhao, Takuya Yoshioka, Zhuo Chen","submitted_at":"2023-09-15T03:55:14Z","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"},"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":"2309.08131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-09-15T03:55:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c38719d6f0b43c284815bdef76c692b29dd6386110a537614a13cf626e48c947","abstract_canon_sha256":"333faf42a4094cacd2da0ba09b0c68fda6f7902b5f6aa0cd76173bc606a3bbc4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:02.424877Z","signature_b64":"02qJAou4KMRBAbgCBk6YRsx2faU7RdwWwjjL79uguYfAi5+Bx/S4C8jcUpnHfxou+IkYjmZhWR4LBYJEGMN6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee563370ece4e11283eaf61f2c5ad831e196da02945ca9e0443f64949aeef2b6","last_reissued_at":"2026-07-05T06:51:02.424474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:02.424474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"t-SOT FNT: Streaming Multi-talker ASR with Text-only Domain Adaptation Capability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Rui Zhao, Takuya Yoshioka, Zhuo Chen","submitted_at":"2023-09-15T03:55:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08131","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/2309.08131/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":"2309.08131","created_at":"2026-07-05T06:51:02.424527+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08131v1","created_at":"2026-07-05T06:51:02.424527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08131","created_at":"2026-07-05T06:51:02.424527+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZLDG4HM4TQR","created_at":"2026-07-05T06:51:02.424527+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZLDG4HM4TQRFA7K","created_at":"2026-07-05T06:51:02.424527+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZLDG4HM","created_at":"2026-07-05T06:51:02.424527+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/5ZLDG4HM4TQRFA7K6YPSYWWYGH","json":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH.json","graph_json":"https://pith.science/api/pith-number/5ZLDG4HM4TQRFA7K6YPSYWWYGH/graph.json","events_json":"https://pith.science/api/pith-number/5ZLDG4HM4TQRFA7K6YPSYWWYGH/events.json","paper":"https://pith.science/paper/5ZLDG4HM"},"agent_actions":{"view_html":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH","download_json":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH.json","view_paper":"https://pith.science/paper/5ZLDG4HM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08131&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZLDG4HM4TQRFA7K6YPSYWWYGH/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZLDG4HM4TQRFA7K6YPSYWWYGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH/action/storage_attestation","attest_author":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH/action/author_attestation","sign_citation":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH/action/citation_signature","submit_replication":"https://pith.science/pith/5ZLDG4HM4TQRFA7K6YPSYWWYGH/action/replication_record"}},"created_at":"2026-07-05T06:51:02.424527+00:00","updated_at":"2026-07-05T06:51:02.424527+00:00"}