{"id":"https://openalex.org/W4375869424","doi":"https://doi.org/10.1109/icassp49357.2023.10096049","title":"The Pipeline System of ASR and NLU with MLM-based data Augmentation Toward Stop Low-Resource Challenge","display_name":"The Pipeline System of ASR and NLU with MLM-based data Augmentation Toward Stop Low-Resource Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869424","doi":"https://doi.org/10.1109/icassp49357.2023.10096049"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034216052","display_name":"Hayato Futami","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hayato Futami","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025385720","display_name":"Jessica Huynh","orcid":"https://orcid.org/0000-0001-5868-5522"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica Huynh","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Arora","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073482068","display_name":"Shih-Lun Wu","orcid":"https://orcid.org/0000-0002-8315-0762"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shih-Lun Wu","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103125256","display_name":"Brian Yan","orcid":"https://orcid.org/0000-0002-4160-6282"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Yan","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5034216052"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6967,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7438934,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7985880374908447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887106537818909},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7746609449386597},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6196452379226685},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.6060525178909302},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5856760740280151},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.5521857738494873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4216909110546112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3445119261741638}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7985880374908447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887106537818909},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7746609449386597},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6196452379226685},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.6060525178909302},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5856760740280151},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.5521857738494873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4216909110546112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3445119261741638},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096049","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307110","display_name":"Delta","ror":"https://ror.org/03g9c1e75"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W3101569935","https://openalex.org/W3104713013","https://openalex.org/W4298186941","https://openalex.org/W4311000453","https://openalex.org/W4319862713","https://openalex.org/W6839924907","https://openalex.org/W6843997150","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W3203792196","https://openalex.org/W2955455867","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"system":[4],"for":[5,47,116],"the":[6,31,59,121,125],"low-resource":[7,65],"domain":[8,49,66],"adaptation":[9],"track":[10],"(Track":[11],"3)":[12],"in":[13],"Spoken":[14],"Language":[15],"Understanding":[16],"Grand":[17,27],"Challenge,":[18],"which":[19],"is":[20,98],"a":[21,35,92,105],"part":[22],"of":[23,38,78],"ICASSP":[24],"Signal":[25],"Processing":[26],"Challenge":[28],"2023.":[29],"In":[30],"track,":[32],"we":[33,44,54,107],"adopt":[34],"pipeline":[36],"approach":[37],"ASR":[39],"and":[40,62,81,119],"NLU.":[41],"For":[42,52],"ASR,":[43],"fine-tune":[45,55],"Whisper":[46],"each":[48],"with":[50,100],"upsampling.":[51],"NLU,":[53],"BART":[56],"on":[57,64],"all":[58],"Track3":[60],"data":[61,74],"then":[63],"data.":[67],"We":[68,89],"apply":[69,91],"masked":[70],"LM":[71],"(MLM)":[72],"-based":[73],"augmentation,":[75],"where":[76,95],"some":[77],"input":[79,97],"tokens":[80],"corresponding":[82],"target":[83],"labels":[84],"are":[85],"replaced":[86],"using":[87],"MLM.":[88],"also":[90],"retrieval-based":[93],"approach,":[94],"model":[96],"augmented":[99],"similar":[101],"training":[102],"samples.":[103],"As":[104],"result,":[106],"achieved":[108],"exact":[109],"match":[110],"(EM)":[111],"accuracy":[112],"63.3/75.0":[113],"(average:":[114],"69.15)":[115],"reminder/weather":[117],"domain,":[118],"won":[120],"1st":[122],"place":[123],"at":[124],"challenge.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}