{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IDGGIM66CW5GDBLQRINKSVJ2L3","short_pith_number":"pith:IDGGIM66","schema_version":"1.0","canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","source":{"kind":"arxiv","id":"2306.01942","version":1},"attestation_state":"computed","paper":{"title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Guangzhi Sun, Philip C. Woodland, Xianrui Zheng","submitted_at":"2023-06-02T22:56:01Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent content words that occur in a particular task may still exhibit poor ASR performance, with contextual biasing a possible remedy. This paper investigates the effectiveness of neural contextual biasing for Whisper combined with GPT-2. Specifically, this paper proposes integrating an adapted tree-constrained pointer generator (TCPGen) component for Whisper and a dedicated training s"},"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":"2306.01942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-02T22:56:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d519e85f57ba7d11bcaf295a5158e9122ee5123352d2e6aa8bee332dc6d0bd38","abstract_canon_sha256":"fb5e4dbcfed23d3c9172be4905628febf12dbca1971273a02b7106b6e9c0830c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:11.262264Z","signature_b64":"PQtF7BLVEa8FGJVbgmROOwBG3Er3Rpr7pCJjmmjf/n/bKBHfJIGkihF6lt45xuBXqDnALHh9HYPqRIoWMvYXCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40cc6433de15ba6185708a1aa9553a5efab453b56a4d5e660d0c29c9c6b4d0fe","last_reissued_at":"2026-07-05T06:17:11.261826Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:11.261826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Contextual Biasing Remain Effective with Whisper and GPT-2?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Guangzhi Sun, Philip C. Woodland, Xianrui Zheng","submitted_at":"2023-06-02T22:56:01Z","abstract_excerpt":"End-to-end automatic speech recognition (ASR) and large language models, such as Whisper and GPT-2, have recently been scaled to use vast amounts of training data. Despite the large amount of training data, infrequent content words that occur in a particular task may still exhibit poor ASR performance, with contextual biasing a possible remedy. This paper investigates the effectiveness of neural contextual biasing for Whisper combined with GPT-2. Specifically, this paper proposes integrating an adapted tree-constrained pointer generator (TCPGen) component for Whisper and a dedicated training s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01942","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/2306.01942/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":"2306.01942","created_at":"2026-07-05T06:17:11.261901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.01942v1","created_at":"2026-07-05T06:17:11.261901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01942","created_at":"2026-07-05T06:17:11.261901+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDGGIM66CW5G","created_at":"2026-07-05T06:17:11.261901+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDGGIM66CW5GDBLQ","created_at":"2026-07-05T06:17:11.261901+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDGGIM66","created_at":"2026-07-05T06:17:11.261901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19157","citing_title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3","json":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3.json","graph_json":"https://pith.science/api/pith-number/IDGGIM66CW5GDBLQRINKSVJ2L3/graph.json","events_json":"https://pith.science/api/pith-number/IDGGIM66CW5GDBLQRINKSVJ2L3/events.json","paper":"https://pith.science/paper/IDGGIM66"},"agent_actions":{"view_html":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3","download_json":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3.json","view_paper":"https://pith.science/paper/IDGGIM66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.01942&json=true","fetch_graph":"https://pith.science/api/pith-number/IDGGIM66CW5GDBLQRINKSVJ2L3/graph.json","fetch_events":"https://pith.science/api/pith-number/IDGGIM66CW5GDBLQRINKSVJ2L3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/action/storage_attestation","attest_author":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/action/author_attestation","sign_citation":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/action/citation_signature","submit_replication":"https://pith.science/pith/IDGGIM66CW5GDBLQRINKSVJ2L3/action/replication_record"}},"created_at":"2026-07-05T06:17:11.261901+00:00","updated_at":"2026-07-05T06:17:11.261901+00:00"}