{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:752JZ6O4AFM3KQXIBOGSYNKFME","short_pith_number":"pith:752JZ6O4","schema_version":"1.0","canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","source":{"kind":"arxiv","id":"2406.10052","version":1},"attestation_state":"computed","paper":{"title":"Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guodong Lin, Guoqiang Hu, Haoyu Wang, Jian Li, Wei-Qiang Zhang","submitted_at":"2024-06-14T14:07:26Z","abstract_excerpt":"As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to streaming speech recognition. In this paper, we introduce Simul-Whisper, which uses the time alignment embedded in Whisper's cross-attention to guide auto-regressive decoding and achieve chunk-based streaming ASR without any fine-tuning of the pre-trained model. Furthermore, we observe the negative effect of the truncated words at the chunk boundaries on the decodi"},"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":"2406.10052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T14:07:26Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"68b51d3c74b0d905ba9e40355ac3b2e9a39b93b4ad75d5495671e150552d57e0","abstract_canon_sha256":"b13c15399b0f462bc2a1558ee448a494e613f83c51f74ef82b016c1e8e7ac591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:52.990504Z","signature_b64":"4NKgeUFdjoUnVWpIBQ2ZEKnelQIytYw8j0YPnAn5GtpGH4QfzMVXaIRM3UM4ysOw7tY2AtAW1Z0C821DHv1yAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff749cf9dc0159b542e80b8d2c35456126358ef7b8a4e8940ddeba6b08acfbd4","last_reissued_at":"2026-07-05T10:57:52.990010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:52.990010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simul-Whisper: Attention-Guided Streaming Whisper with Truncation Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guodong Lin, Guoqiang Hu, Haoyu Wang, Jian Li, Wei-Qiang Zhang","submitted_at":"2024-06-14T14:07:26Z","abstract_excerpt":"As a robust and large-scale multilingual speech recognition model, Whisper has demonstrated impressive results in many low-resource and out-of-distribution scenarios. However, its encoder-decoder structure hinders its application to streaming speech recognition. In this paper, we introduce Simul-Whisper, which uses the time alignment embedded in Whisper's cross-attention to guide auto-regressive decoding and achieve chunk-based streaming ASR without any fine-tuning of the pre-trained model. Furthermore, we observe the negative effect of the truncated words at the chunk boundaries on the decodi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10052","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/2406.10052/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":"2406.10052","created_at":"2026-07-05T10:57:52.990067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10052v1","created_at":"2026-07-05T10:57:52.990067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10052","created_at":"2026-07-05T10:57:52.990067+00:00"},{"alias_kind":"pith_short_12","alias_value":"752JZ6O4AFM3","created_at":"2026-07-05T10:57:52.990067+00:00"},{"alias_kind":"pith_short_16","alias_value":"752JZ6O4AFM3KQXI","created_at":"2026-07-05T10:57:52.990067+00:00"},{"alias_kind":"pith_short_8","alias_value":"752JZ6O4","created_at":"2026-07-05T10:57:52.990067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01108","citing_title":"NPUsper: Eliminating Redundant Computation for Real-Time Whisper on Mobile NPUs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2508.12301","citing_title":"WhisperRT -- Turning Whisper into a Causal Streaming Model","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME","json":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME.json","graph_json":"https://pith.science/api/pith-number/752JZ6O4AFM3KQXIBOGSYNKFME/graph.json","events_json":"https://pith.science/api/pith-number/752JZ6O4AFM3KQXIBOGSYNKFME/events.json","paper":"https://pith.science/paper/752JZ6O4"},"agent_actions":{"view_html":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME","download_json":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME.json","view_paper":"https://pith.science/paper/752JZ6O4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10052&json=true","fetch_graph":"https://pith.science/api/pith-number/752JZ6O4AFM3KQXIBOGSYNKFME/graph.json","fetch_events":"https://pith.science/api/pith-number/752JZ6O4AFM3KQXIBOGSYNKFME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/action/storage_attestation","attest_author":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/action/author_attestation","sign_citation":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/action/citation_signature","submit_replication":"https://pith.science/pith/752JZ6O4AFM3KQXIBOGSYNKFME/action/replication_record"}},"created_at":"2026-07-05T10:57:52.990067+00:00","updated_at":"2026-07-05T10:57:52.990067+00:00"}