{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:45DQHKRNB45O6QJIZQNNPRGJTS","short_pith_number":"pith:45DQHKRN","schema_version":"1.0","canonical_sha256":"e74703aa2d0f3aef4128cc1ad7c4c99c97f6da12f22ad43598cccc3abecb8408","source":{"kind":"arxiv","id":"2211.08726","version":2},"attestation_state":"computed","paper":{"title":"Streaming Joint Speech Recognition and Disfluency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Kentaro Shibata, Shinji Watanabe, Siddhant Arora, Takao Okuda, Yosuke Kashiwagi","submitted_at":"2022-11-16T07:34:20Z","abstract_excerpt":"Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection, which work in a streaming manner. Compared to pipeline approaches, the joint models can leverage acoustic information that makes disfluency detection robust to recognition errors and provide non-verbal clues. Moreover, joint modeling results in low-latency and lightweight inference. We investigate two joint model variants for streaming disfluency detection:"},"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":"2211.08726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T07:34:20Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f833c3c50ff0c46b818ce99c269f7e2b1285a8e4d526e25bb181af2cfd92b5ba","abstract_canon_sha256":"c36b78c3dd984daa3962db5db7b986237ec869cb737b93711d01ccd71a743257"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:06.798773Z","signature_b64":"oT3nk6VIs2Nt6oMNpDpi9YLyh0Yrh7HItfI16AJkDcK9mSsMQxhPIC+nemmsom/V0eejvrFNnOCMfaDX86TRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e74703aa2d0f3aef4128cc1ad7c4c99c97f6da12f22ad43598cccc3abecb8408","last_reissued_at":"2026-07-05T06:09:06.798284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:06.798284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Joint Speech Recognition and Disfluency Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Emiru Tsunoo, Hayato Futami, Kentaro Shibata, Shinji Watanabe, Siddhant Arora, Takao Okuda, Yosuke Kashiwagi","submitted_at":"2022-11-16T07:34:20Z","abstract_excerpt":"Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection, which work in a streaming manner. Compared to pipeline approaches, the joint models can leverage acoustic information that makes disfluency detection robust to recognition errors and provide non-verbal clues. Moreover, joint modeling results in low-latency and lightweight inference. We investigate two joint model variants for streaming disfluency detection:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08726","kind":"arxiv","version":2},"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/2211.08726/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":"2211.08726","created_at":"2026-07-05T06:09:06.798355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08726v2","created_at":"2026-07-05T06:09:06.798355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08726","created_at":"2026-07-05T06:09:06.798355+00:00"},{"alias_kind":"pith_short_12","alias_value":"45DQHKRNB45O","created_at":"2026-07-05T06:09:06.798355+00:00"},{"alias_kind":"pith_short_16","alias_value":"45DQHKRNB45O6QJI","created_at":"2026-07-05T06:09:06.798355+00:00"},{"alias_kind":"pith_short_8","alias_value":"45DQHKRN","created_at":"2026-07-05T06:09:06.798355+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/45DQHKRNB45O6QJIZQNNPRGJTS","json":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS.json","graph_json":"https://pith.science/api/pith-number/45DQHKRNB45O6QJIZQNNPRGJTS/graph.json","events_json":"https://pith.science/api/pith-number/45DQHKRNB45O6QJIZQNNPRGJTS/events.json","paper":"https://pith.science/paper/45DQHKRN"},"agent_actions":{"view_html":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS","download_json":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS.json","view_paper":"https://pith.science/paper/45DQHKRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08726&json=true","fetch_graph":"https://pith.science/api/pith-number/45DQHKRNB45O6QJIZQNNPRGJTS/graph.json","fetch_events":"https://pith.science/api/pith-number/45DQHKRNB45O6QJIZQNNPRGJTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS/action/storage_attestation","attest_author":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS/action/author_attestation","sign_citation":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS/action/citation_signature","submit_replication":"https://pith.science/pith/45DQHKRNB45O6QJIZQNNPRGJTS/action/replication_record"}},"created_at":"2026-07-05T06:09:06.798355+00:00","updated_at":"2026-07-05T06:09:06.798355+00:00"}