{"id":"https://openalex.org/W4372268584","doi":"https://doi.org/10.1109/icassp49357.2023.10096175","title":"A Study on the Integration of Pipeline and E2E SLU Systems for Spoken Semantic Parsing Toward Stop Quality Challenge","display_name":"A Study on the Integration of Pipeline and E2E SLU Systems for Spoken Semantic Parsing Toward Stop Quality Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372268584","doi":"https://doi.org/10.1109/icassp49357.2023.10096175"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096175","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096175","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":"conference-paper","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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034216052","display_name":"Hayato Futami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hayato Futami","raw_affiliation_strings":["Sony Group Corporation,Japan","Sony Group Corporation, Japan"],"raw_orcid":null,"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/A5088967620","display_name":"Shih-Lun Wu","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081742816","display_name":"Jessica Huynh","orcid":"https://orcid.org/0009-0007-2821-7315"},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","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"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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/A5021201726","display_name":"Brian Yan","orcid":null},"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.436,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55472884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8895701766014099},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.771926999092102},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.7685961723327637},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7662658095359802},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7152791023254395},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6350317001342773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6239737868309021},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5715162754058838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5495362877845764},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.48768317699432373},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42918169498443604},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.42309510707855225},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13772818446159363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8895701766014099},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.771926999092102},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.7685961723327637},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7662658095359802},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7152791023254395},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6350317001342773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6239737868309021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5715162754058838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5495362877845764},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.48768317699432373},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42918169498443604},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.42309510707855225},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13772818446159363},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096175","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096175","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W4226302523","https://openalex.org/W4297841571","https://openalex.org/W4319862713"],"related_works":["https://openalex.org/W2789518417","https://openalex.org/W4213217485","https://openalex.org/W2566545183","https://openalex.org/W2499449816","https://openalex.org/W2059085722","https://openalex.org/W4210856988","https://openalex.org/W238145802","https://openalex.org/W579810227","https://openalex.org/W2946721565","https://openalex.org/W2801976440"],"abstract_inverted_index":{"Recently":[0],"there":[1],"have":[2],"been":[3],"efforts":[4],"to":[5,83,96],"introduce":[6],"new":[7],"benchmark":[8],"tasks":[9],"for":[10,29,59],"spoken":[11,25],"language":[12],"understanding":[13],"(SLU),":[14],"like":[15,68,75],"semantic":[16,26],"parsing.":[17],"In":[18],"this":[19,60],"paper,":[20],"we":[21],"describe":[22],"our":[23,80],"proposed":[24],"parsing":[27],"system":[28],"the":[30,89,106,110],"quality":[31],"track":[32],"(Track":[33],"1)":[34],"in":[35],"Spoken":[36],"Language":[37,72],"Understanding":[38],"Grand":[39,48],"Challenge":[40,49],"which":[41,104],"is":[42],"part":[43],"of":[44,93,102],"ICASSP":[45],"Signal":[46],"Processing":[47],"2023.":[50],"We":[51,86],"experiment":[52],"with":[53],"both":[54],"end-to-end":[55],"and":[56,70],"pipeline":[57],"systems":[58],"task.":[61],"Strong":[62],"automatic":[63],"speech":[64],"recognition":[65],"(ASR)":[66],"models":[67,73,95],"Whisper":[69],"pretrained":[71],"(LM)":[74],"BART":[76],"are":[77],"utilized":[78],"inside":[79],"SLU":[81],"framework":[82],"boost":[84],"performance.":[85],"also":[87],"investigate":[88],"output":[90],"level":[91],"combination":[92],"various":[94],"get":[97],"an":[98],"exact":[99],"match":[100],"accuracy":[101],"80.8,":[103],"won":[105],"1st":[107],"place":[108],"at":[109],"challenge.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
