{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7IOBEVVEZPGNFINVUC4DGS3ZRE","short_pith_number":"pith:7IOBEVVE","schema_version":"1.0","canonical_sha256":"fa1c1256a4cbccd2a1b5a0b8334b79893bf97dc844003beeacaf3e9ff667d643","source":{"kind":"arxiv","id":"2307.11005","version":1},"attestation_state":"computed","paper":{"title":"Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-07-20T16:34:40Z","abstract_excerpt":"There has been an increased interest in the integration of pretrained speech recognition (ASR) and language models (LM) into the SLU framework. However, prior methods often struggle with a vocabulary mismatch between pretrained models, and LM cannot be directly utilized as they diverge from its NLU formulation. In this study, we propose a three-pass end-to-end (E2E) SLU system that effectively integrates ASR and LM subnetworks into the SLU formulation for sequence generation tasks. In the first pass, our architecture predicts ASR transcripts using the ASR subnetwork. This is followed by the LM"},"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":"2307.11005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-20T16:34:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"e3d9c0910b241839e11e9c6740af9187cf6e7c6cdcff8dc896282a9e85b4d194","abstract_canon_sha256":"460b0865924f22a0ef1ff1568a21d62deaffc9de60c2435b2870922b4e879fb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:14.043359Z","signature_b64":"mRc0at/E6oBJh0vvv/1rotIUi7m6EPUI2YY4jLvakvqzEPANP80wujeKh6ixbOUpvIiVJAtUuYHQhfxmiz7TBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa1c1256a4cbccd2a1b5a0b8334b79893bf97dc844003beeacaf3e9ff667d643","last_reissued_at":"2026-07-05T06:33:14.042924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:14.042924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Integrating Pretrained ASR and LM to Perform Sequence Generation for Spoken Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Brian Yan, Emiru Tsunoo, Hayato Futami, Shinji Watanabe, Siddhant Arora, Yosuke Kashiwagi","submitted_at":"2023-07-20T16:34:40Z","abstract_excerpt":"There has been an increased interest in the integration of pretrained speech recognition (ASR) and language models (LM) into the SLU framework. However, prior methods often struggle with a vocabulary mismatch between pretrained models, and LM cannot be directly utilized as they diverge from its NLU formulation. In this study, we propose a three-pass end-to-end (E2E) SLU system that effectively integrates ASR and LM subnetworks into the SLU formulation for sequence generation tasks. In the first pass, our architecture predicts ASR transcripts using the ASR subnetwork. This is followed by the LM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11005","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/2307.11005/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":"2307.11005","created_at":"2026-07-05T06:33:14.042979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11005v1","created_at":"2026-07-05T06:33:14.042979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11005","created_at":"2026-07-05T06:33:14.042979+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IOBEVVEZPGN","created_at":"2026-07-05T06:33:14.042979+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IOBEVVEZPGNFINV","created_at":"2026-07-05T06:33:14.042979+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IOBEVVE","created_at":"2026-07-05T06:33:14.042979+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/7IOBEVVEZPGNFINVUC4DGS3ZRE","json":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE.json","graph_json":"https://pith.science/api/pith-number/7IOBEVVEZPGNFINVUC4DGS3ZRE/graph.json","events_json":"https://pith.science/api/pith-number/7IOBEVVEZPGNFINVUC4DGS3ZRE/events.json","paper":"https://pith.science/paper/7IOBEVVE"},"agent_actions":{"view_html":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE","download_json":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE.json","view_paper":"https://pith.science/paper/7IOBEVVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11005&json=true","fetch_graph":"https://pith.science/api/pith-number/7IOBEVVEZPGNFINVUC4DGS3ZRE/graph.json","fetch_events":"https://pith.science/api/pith-number/7IOBEVVEZPGNFINVUC4DGS3ZRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE/action/storage_attestation","attest_author":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE/action/author_attestation","sign_citation":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE/action/citation_signature","submit_replication":"https://pith.science/pith/7IOBEVVEZPGNFINVUC4DGS3ZRE/action/replication_record"}},"created_at":"2026-07-05T06:33:14.042979+00:00","updated_at":"2026-07-05T06:33:14.042979+00:00"}