{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RSP46HPTHPD5JBXNBVW2IJ56ZO","short_pith_number":"pith:RSP46HPT","schema_version":"1.0","canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","source":{"kind":"arxiv","id":"2406.09950","version":1},"attestation_state":"computed","paper":{"title":"An efficient text augmentation approach for contextualized Mandarin speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Liu, Naijun Zheng, Xucheng Wan, Zhou Huan, Ziqing Du","submitted_at":"2024-06-14T11:53:14Z","abstract_excerpt":"Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this challenge, our study proposes to leverage extensive text-only datasets and contextualize pre-trained ASR models using a straightforward text-augmentation (TA) technique, all while keeping computational costs minimal. In particular, to contextualize a pre-trained CIF-based ASR, we construct a codebook using limited speech-text data. By utilizing a simple cod"},"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":"2406.09950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-14T11:53:14Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"cb615d5bf8e45cfc529cc53b62ca82b45aa182c05feb85625f815b5d4e041d93","abstract_canon_sha256":"aa8b3918ded87f10e0f810c18d3822d066efb61bba87fc041410710bb15ac48d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:02.386499Z","signature_b64":"LkcNylD/XUGzb8uYuqg6zlFcir6ss8ThL5EhGYXBFv8HBzYT5o/IfCAzLYdiqL6Sjcl0x489CSZEmM5ckgsFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c9fcf1df33bc7d486ed0d6da427becbbd8b9c0473b0743c4ab3df8d2baeb7e3","last_reissued_at":"2026-07-05T08:32:02.385901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:02.385901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An efficient text augmentation approach for contextualized Mandarin speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Liu, Naijun Zheng, Xucheng Wan, Zhou Huan, Ziqing Du","submitted_at":"2024-06-14T11:53:14Z","abstract_excerpt":"Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this challenge, our study proposes to leverage extensive text-only datasets and contextualize pre-trained ASR models using a straightforward text-augmentation (TA) technique, all while keeping computational costs minimal. In particular, to contextualize a pre-trained CIF-based ASR, we construct a codebook using limited speech-text data. By utilizing a simple cod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09950","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/2406.09950/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":"2406.09950","created_at":"2026-07-05T08:32:02.385989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09950v1","created_at":"2026-07-05T08:32:02.385989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09950","created_at":"2026-07-05T08:32:02.385989+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSP46HPTHPD5","created_at":"2026-07-05T08:32:02.385989+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSP46HPTHPD5JBXN","created_at":"2026-07-05T08:32:02.385989+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSP46HPT","created_at":"2026-07-05T08:32:02.385989+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/RSP46HPTHPD5JBXNBVW2IJ56ZO","json":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO.json","graph_json":"https://pith.science/api/pith-number/RSP46HPTHPD5JBXNBVW2IJ56ZO/graph.json","events_json":"https://pith.science/api/pith-number/RSP46HPTHPD5JBXNBVW2IJ56ZO/events.json","paper":"https://pith.science/paper/RSP46HPT"},"agent_actions":{"view_html":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO","download_json":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO.json","view_paper":"https://pith.science/paper/RSP46HPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09950&json=true","fetch_graph":"https://pith.science/api/pith-number/RSP46HPTHPD5JBXNBVW2IJ56ZO/graph.json","fetch_events":"https://pith.science/api/pith-number/RSP46HPTHPD5JBXNBVW2IJ56ZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/action/storage_attestation","attest_author":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/action/author_attestation","sign_citation":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/action/citation_signature","submit_replication":"https://pith.science/pith/RSP46HPTHPD5JBXNBVW2IJ56ZO/action/replication_record"}},"created_at":"2026-07-05T08:32:02.385989+00:00","updated_at":"2026-07-05T08:32:02.385989+00:00"}