{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CDVY7AEKQ4ZQFTT7KHHAVVOTJO","short_pith_number":"pith:CDVY7AEK","schema_version":"1.0","canonical_sha256":"10eb8f808a873302ce7f51ce0ad5d34bb4e00bd93c3b0b525016a635e9514a89","source":{"kind":"arxiv","id":"2305.01194","version":2},"attestation_state":"computed","paper":{"title":"The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge","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, Jessica Huynh, Shih-Lun Wu, Shinji Watanabe, Siddhant Arora, Yifan Peng, Yosuke Kashiwagi","submitted_at":"2023-05-02T04:03:30Z","abstract_excerpt":"This paper describes our system for the low-resource domain adaptation track (Track 3) in Spoken Language Understanding Grand Challenge, which is a part of ICASSP Signal Processing Grand Challenge 2023. In the track, we adopt a pipeline approach of ASR and NLU. For ASR, we fine-tune Whisper for each domain with upsampling. For NLU, we fine-tune BART on all the Track3 data and then on low-resource domain data. We apply masked LM (MLM) -based data augmentation, where some of input tokens and corresponding target labels are replaced using MLM. We also apply a retrieval-based approach, where model"},"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":"2305.01194","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-02T04:03:30Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2c6b7f98a67e4065732c24b7e7f3c113386c7eaa4aaa1935bf9adde863781757","abstract_canon_sha256":"50c684f375a4eb99e6e11fe48bf8a7665e5140c818addd175805e478356a57d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:10.076644Z","signature_b64":"GvBmcVZrvSH0cqXY2GtOiQ/5O055NRjhiURY/hBMeegDpsE6x98UUUz8jBn1znVXYWRanBgXdTbS2Safr2qUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10eb8f808a873302ce7f51ce0ad5d34bb4e00bd93c3b0b525016a635e9514a89","last_reissued_at":"2026-07-05T06:09:10.076183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:10.076183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Pipeline System of ASR and NLU with MLM-based Data Augmentation toward STOP Low-resource Challenge","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, Jessica Huynh, Shih-Lun Wu, Shinji Watanabe, Siddhant Arora, Yifan Peng, Yosuke Kashiwagi","submitted_at":"2023-05-02T04:03:30Z","abstract_excerpt":"This paper describes our system for the low-resource domain adaptation track (Track 3) in Spoken Language Understanding Grand Challenge, which is a part of ICASSP Signal Processing Grand Challenge 2023. In the track, we adopt a pipeline approach of ASR and NLU. For ASR, we fine-tune Whisper for each domain with upsampling. For NLU, we fine-tune BART on all the Track3 data and then on low-resource domain data. We apply masked LM (MLM) -based data augmentation, where some of input tokens and corresponding target labels are replaced using MLM. We also apply a retrieval-based approach, where model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01194","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/2305.01194/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":"2305.01194","created_at":"2026-07-05T06:09:10.076243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.01194v2","created_at":"2026-07-05T06:09:10.076243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01194","created_at":"2026-07-05T06:09:10.076243+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDVY7AEKQ4ZQ","created_at":"2026-07-05T06:09:10.076243+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDVY7AEKQ4ZQFTT7","created_at":"2026-07-05T06:09:10.076243+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDVY7AEK","created_at":"2026-07-05T06:09:10.076243+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/CDVY7AEKQ4ZQFTT7KHHAVVOTJO","json":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO.json","graph_json":"https://pith.science/api/pith-number/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/graph.json","events_json":"https://pith.science/api/pith-number/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/events.json","paper":"https://pith.science/paper/CDVY7AEK"},"agent_actions":{"view_html":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO","download_json":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO.json","view_paper":"https://pith.science/paper/CDVY7AEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.01194&json=true","fetch_graph":"https://pith.science/api/pith-number/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/graph.json","fetch_events":"https://pith.science/api/pith-number/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/action/storage_attestation","attest_author":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/action/author_attestation","sign_citation":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/action/citation_signature","submit_replication":"https://pith.science/pith/CDVY7AEKQ4ZQFTT7KHHAVVOTJO/action/replication_record"}},"created_at":"2026-07-05T06:09:10.076243+00:00","updated_at":"2026-07-05T06:09:10.076243+00:00"}