{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OQWRAWNEV3JYCTH5XTJR3KVMZ2","short_pith_number":"pith:OQWRAWNE","schema_version":"1.0","canonical_sha256":"742d1059a4aed3814cfdbcd31daaaccebd9aa71fa82769506ee6a5c34789be71","source":{"kind":"arxiv","id":"2605.18222","version":1},"attestation_state":"computed","paper":{"title":"Contextual Biasing for Streaming ASR via CTC-based Word Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A streaming extension of CTC-based word spotting enables real-time contextual biasing in ASR by tracking keyword paths across chunks and committing only to stable segments.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Kai-Chen Tsai, Tien-Hong Lo, Yun-Ting Sun","submitted_at":"2026-05-18T11:06:44Z","abstract_excerpt":"Contextual biasing is essential to improving the recognition of rare and domain-specific words in an automatic speech recognition (ASR) system. While numerous methods have been proposed in recent years, most of them focus on offline settings and do not explicitly address the challenges of streaming ASR. For example, CTC-based word spotting (CTC-WS) have demonstrated strong performance by directly detecting keywords from CTC log-probabilities, but they are limited to offline processing and require access to the full utterance. In This work, we present a streaming extension of CTC-WS for real-ti"},"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":"2605.18222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T11:06:44Z","cross_cats_sorted":[],"title_canon_sha256":"3f8df42c862067ab610b02bc55b5068d868d9b241e92c1a041f52a14bd4694ee","abstract_canon_sha256":"208efa60de962a0ea7e350b8682dac41b6c1ce2304b0736ea2c26945c0e4fde7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:51.151450Z","signature_b64":"gMvheeeaSEXVUWQeKjFmZ2PMRIRtezNwTUpVHnime6uWHqgXzeEtF98OQIRx1ag3CBocnDmp8ZIA9y139tojCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742d1059a4aed3814cfdbcd31daaaccebd9aa71fa82769506ee6a5c34789be71","last_reissued_at":"2026-05-20T00:05:51.150826Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:51.150826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Biasing for Streaming ASR via CTC-based Word Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A streaming extension of CTC-based word spotting enables real-time contextual biasing in ASR by tracking keyword paths across chunks and committing only to stable segments.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Berlin Chen, Kai-Chen Tsai, Tien-Hong Lo, Yun-Ting Sun","submitted_at":"2026-05-18T11:06:44Z","abstract_excerpt":"Contextual biasing is essential to improving the recognition of rare and domain-specific words in an automatic speech recognition (ASR) system. While numerous methods have been proposed in recent years, most of them focus on offline settings and do not explicitly address the challenges of streaming ASR. For example, CTC-based word spotting (CTC-WS) have demonstrated strong performance by directly detecting keywords from CTC log-probabilities, but they are limited to offline processing and require access to the full utterance. In This work, we present a streaming extension of CTC-WS for real-ti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results show that our method reduces overall WER and effectively improves keyword F-score, demonstrating its effectiveness for real-time ASR applications.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The incremental commitment mechanism successfully identifies segments guaranteed not to be affected by future audio while deferring uncertain regions, enabling both low latency and stable output without harming overall accuracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces a streaming CTC-WS method with stateful token passing and incremental commitment for low-latency contextual biasing in ASR, claiming reduced WER and improved keyword F-score.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A streaming extension of CTC-based word spotting enables real-time contextual biasing in ASR by tracking keyword paths across chunks and committing only to stable segments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"347bfc65c0836d423d48ab89dedb2fb6db229adc3892acb844685a873606c7b1"},"source":{"id":"2605.18222","kind":"arxiv","version":1},"verdict":{"id":"1baa6f63-9cfa-499c-a4b7-9777bc6bc772","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-20T00:00:05.717483Z","strongest_claim":"Experimental results show that our method reduces overall WER and effectively improves keyword F-score, demonstrating its effectiveness for real-time ASR applications.","one_line_summary":"Introduces a streaming CTC-WS method with stateful token passing and incremental commitment for low-latency contextual biasing in ASR, claiming reduced WER and improved keyword F-score.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The incremental commitment mechanism successfully identifies segments guaranteed not to be affected by future audio while deferring uncertain regions, enabling both low latency and stable output without harming overall accuracy.","pith_extraction_headline":"A streaming extension of CTC-based word spotting enables real-time contextual biasing in ASR by tracking keyword paths across chunks and committing only to stable segments."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.18222/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:58.952786Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.300328Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"cf41e06bbb0234748f78172c7c3b34fe4699be94c576aa56003641c83542a743"},"references":{"count":18,"sample":[{"doi":"","year":2022,"title":"A Survey on Deep Learning for Named Entity Recognition,","work_id":"","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Deep Context: End-to-End Contextual Speech Recognition,","work_id":"","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Contextual RNN-T for Open Domain ASR,","work_id":"","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"PromptASR for Contextualized ASR with Controllable Style,","work_id":"","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Contextualized Streaming End-to-End Speech Recognition with Trie- Based Deep Biasing and Shallow Fusion,","work_id":"","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":0,"snapshot_sha256":"65f14c318062429b4e0754cc4600fd9f10503ed239fed4772edc5bac86e3e4a3","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":"2605.18222","created_at":"2026-05-20T00:05:51.150908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18222v1","created_at":"2026-05-20T00:05:51.150908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18222","created_at":"2026-05-20T00:05:51.150908+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQWRAWNEV3JY","created_at":"2026-05-20T00:05:51.150908+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQWRAWNEV3JYCTH5","created_at":"2026-05-20T00:05:51.150908+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQWRAWNE","created_at":"2026-05-20T00:05:51.150908+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/OQWRAWNEV3JYCTH5XTJR3KVMZ2","json":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2.json","graph_json":"https://pith.science/api/pith-number/OQWRAWNEV3JYCTH5XTJR3KVMZ2/graph.json","events_json":"https://pith.science/api/pith-number/OQWRAWNEV3JYCTH5XTJR3KVMZ2/events.json","paper":"https://pith.science/paper/OQWRAWNE"},"agent_actions":{"view_html":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2","download_json":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2.json","view_paper":"https://pith.science/paper/OQWRAWNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18222&json=true","fetch_graph":"https://pith.science/api/pith-number/OQWRAWNEV3JYCTH5XTJR3KVMZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/OQWRAWNEV3JYCTH5XTJR3KVMZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2/action/storage_attestation","attest_author":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2/action/author_attestation","sign_citation":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2/action/citation_signature","submit_replication":"https://pith.science/pith/OQWRAWNEV3JYCTH5XTJR3KVMZ2/action/replication_record"}},"created_at":"2026-05-20T00:05:51.150908+00:00","updated_at":"2026-05-20T00:05:51.150908+00:00"}