{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IREKZDT6SOVIYW66OZU4UANWR4","short_pith_number":"pith:IREKZDT6","schema_version":"1.0","canonical_sha256":"4448ac8e7e93aa8c5bde7669ca01b68f0c082dbf2a2ac60b288760c8a799cde0","source":{"kind":"arxiv","id":"2309.07414","version":3},"attestation_state":"computed","paper":{"title":"PromptASR for contextualized ASR with controllable style","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Fangjun Kuang, Liyong Guo, Long Lin, Wei Kang, Xiaoyu Yang, Yifan Yang, Zengwei Yao","submitted_at":"2023-09-14T03:43:07Z","abstract_excerpt":"Prompts are crucial to large language models as they provide context information such as topic or logical relationships. Inspired by this, we propose PromptASR, a framework that integrates prompts in end-to-end automatic speech recognition (E2E ASR) systems to achieve contextualized ASR with controllable style of transcriptions. Specifically, a dedicated text encoder encodes the text prompts and the encodings are injected into the speech encoder by cross-attending the features from two modalities. When using the ground truth text from preceding utterances as content prompt, the proposed system"},"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":"2309.07414","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-09-14T03:43:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c8a669f8a357715f57921992505ece2445b5504f5fa8bf4bf2a2ae2bc30c8d93","abstract_canon_sha256":"afbcfc682078a924c978327d83d481d93043a90a45c6f705931712e333975863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:54.250232Z","signature_b64":"uD7fZYhXsCAXrSkuuahsyX29eUZEzUCvGLemAwQZPJWNqH76vqxBF0X7cNJ975Kortqu3+/qmJ0NJKVy+Xa1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4448ac8e7e93aa8c5bde7669ca01b68f0c082dbf2a2ac60b288760c8a799cde0","last_reissued_at":"2026-07-05T07:36:54.249797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:54.249797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptASR for contextualized ASR with controllable style","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daniel Povey, Fangjun Kuang, Liyong Guo, Long Lin, Wei Kang, Xiaoyu Yang, Yifan Yang, Zengwei Yao","submitted_at":"2023-09-14T03:43:07Z","abstract_excerpt":"Prompts are crucial to large language models as they provide context information such as topic or logical relationships. Inspired by this, we propose PromptASR, a framework that integrates prompts in end-to-end automatic speech recognition (E2E ASR) systems to achieve contextualized ASR with controllable style of transcriptions. Specifically, a dedicated text encoder encodes the text prompts and the encodings are injected into the speech encoder by cross-attending the features from two modalities. When using the ground truth text from preceding utterances as content prompt, the proposed system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07414","kind":"arxiv","version":3},"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/2309.07414/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":"2309.07414","created_at":"2026-07-05T07:36:54.249860+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07414v3","created_at":"2026-07-05T07:36:54.249860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07414","created_at":"2026-07-05T07:36:54.249860+00:00"},{"alias_kind":"pith_short_12","alias_value":"IREKZDT6SOVI","created_at":"2026-07-05T07:36:54.249860+00:00"},{"alias_kind":"pith_short_16","alias_value":"IREKZDT6SOVIYW66","created_at":"2026-07-05T07:36:54.249860+00:00"},{"alias_kind":"pith_short_8","alias_value":"IREKZDT6","created_at":"2026-07-05T07:36:54.249860+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19179","citing_title":"BR-ASR: Efficient and Scalable Bias Retrieval Framework for Contextual Biasing ASR in Speech LLM","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4","json":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4.json","graph_json":"https://pith.science/api/pith-number/IREKZDT6SOVIYW66OZU4UANWR4/graph.json","events_json":"https://pith.science/api/pith-number/IREKZDT6SOVIYW66OZU4UANWR4/events.json","paper":"https://pith.science/paper/IREKZDT6"},"agent_actions":{"view_html":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4","download_json":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4.json","view_paper":"https://pith.science/paper/IREKZDT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07414&json=true","fetch_graph":"https://pith.science/api/pith-number/IREKZDT6SOVIYW66OZU4UANWR4/graph.json","fetch_events":"https://pith.science/api/pith-number/IREKZDT6SOVIYW66OZU4UANWR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4/action/storage_attestation","attest_author":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4/action/author_attestation","sign_citation":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4/action/citation_signature","submit_replication":"https://pith.science/pith/IREKZDT6SOVIYW66OZU4UANWR4/action/replication_record"}},"created_at":"2026-07-05T07:36:54.249860+00:00","updated_at":"2026-07-05T07:36:54.249860+00:00"}