{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSKL3QAJ7KEECVP5DIG5B6MII6","short_pith_number":"pith:PSKL3QAJ","schema_version":"1.0","canonical_sha256":"7c94bdc009fa884155fd1a0dd0f98847951e5d2a36253d3be865dcd25fb78e91","source":{"kind":"arxiv","id":"2401.11382","version":2},"attestation_state":"computed","paper":{"title":"Using Large Language Model for End-to-End Chinese ASR and NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiawei Yu, Jinsong Su, Mengxin Ren, Min Zhang, Shimin Tao, Xiaofeng Zhao, Yanqing Zhao, Yuang Li","submitted_at":"2024-01-21T03:15:05Z","abstract_excerpt":"Mapping speech tokens to the same feature space as text tokens has become the paradigm for the integration of speech modality into decoder-only large language models (LLMs). An alternative approach is to use an encoder-decoder architecture that incorporates speech features through cross-attention. This approach, however, has received less attention in the literature. In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks. We evaluate them not onl"},"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":"2401.11382","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-21T03:15:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cffae694f7392979f3f2ff122540b591fadbef9c91b75d389baceb87fa431300","abstract_canon_sha256":"ae6b6b4e16581f8d47d6ea2b908ef6a5fb490615b85b61936f2f8e63a76cc986"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:05.201247Z","signature_b64":"TLtyanWoJ5lSTNveRBxb1pglXhJPPLHUIbjcbP5ri93NpbYWriNUywwPSrrp0Wsr+8jafHZ0EdpMV0mPySwLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c94bdc009fa884155fd1a0dd0f98847951e5d2a36253d3be865dcd25fb78e91","last_reissued_at":"2026-07-05T08:28:05.200813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:05.200813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Large Language Model for End-to-End Chinese ASR and NER","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiawei Yu, Jinsong Su, Mengxin Ren, Min Zhang, Shimin Tao, Xiaofeng Zhao, Yanqing Zhao, Yuang Li","submitted_at":"2024-01-21T03:15:05Z","abstract_excerpt":"Mapping speech tokens to the same feature space as text tokens has become the paradigm for the integration of speech modality into decoder-only large language models (LLMs). An alternative approach is to use an encoder-decoder architecture that incorporates speech features through cross-attention. This approach, however, has received less attention in the literature. In this work, we connect the Whisper encoder with ChatGLM3 and provide in-depth comparisons of these two approaches using Chinese automatic speech recognition (ASR) and name entity recognition (NER) tasks. We evaluate them not onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11382","kind":"arxiv","version":2},"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/2401.11382/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":"2401.11382","created_at":"2026-07-05T08:28:05.200870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11382v2","created_at":"2026-07-05T08:28:05.200870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11382","created_at":"2026-07-05T08:28:05.200870+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSKL3QAJ7KEE","created_at":"2026-07-05T08:28:05.200870+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSKL3QAJ7KEECVP5","created_at":"2026-07-05T08:28:05.200870+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSKL3QAJ","created_at":"2026-07-05T08:28:05.200870+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/PSKL3QAJ7KEECVP5DIG5B6MII6","json":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6.json","graph_json":"https://pith.science/api/pith-number/PSKL3QAJ7KEECVP5DIG5B6MII6/graph.json","events_json":"https://pith.science/api/pith-number/PSKL3QAJ7KEECVP5DIG5B6MII6/events.json","paper":"https://pith.science/paper/PSKL3QAJ"},"agent_actions":{"view_html":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6","download_json":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6.json","view_paper":"https://pith.science/paper/PSKL3QAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11382&json=true","fetch_graph":"https://pith.science/api/pith-number/PSKL3QAJ7KEECVP5DIG5B6MII6/graph.json","fetch_events":"https://pith.science/api/pith-number/PSKL3QAJ7KEECVP5DIG5B6MII6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6/action/storage_attestation","attest_author":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6/action/author_attestation","sign_citation":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6/action/citation_signature","submit_replication":"https://pith.science/pith/PSKL3QAJ7KEECVP5DIG5B6MII6/action/replication_record"}},"created_at":"2026-07-05T08:28:05.200870+00:00","updated_at":"2026-07-05T08:28:05.200870+00:00"}