{"id":"https://openalex.org/W3015412890","doi":"https://doi.org/10.1109/icassp40776.2020.9053163","title":"Large-Scale Unsupervised Pre-Training for End-to-End Spoken Language Understanding","display_name":"Large-Scale Unsupervised Pre-Training for End-to-End Spoken Language Understanding","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015412890","doi":"https://doi.org/10.1109/icassp40776.2020.9053163","mag":"3015412890"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5100614748","display_name":"Pengwei Wang","orcid":"https://orcid.org/0000-0002-5667-3488"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pengwei Wang","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061916742","display_name":"Liangchen Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangchen Wei","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103023862","display_name":"Yong Cao","orcid":"https://orcid.org/0000-0001-7639-7647"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Cao","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041549596","display_name":"Jinghui Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinghui Xie","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaiqing Nie","raw_affiliation_strings":["Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100614748"],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":5.1699,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9618951,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7999","last_page":"8003"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8399934768676758},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8357657194137573},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6339083909988403},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.6299346685409546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5732981562614441},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5631071925163269},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5018472671508789},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49771931767463684},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4934329092502594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4726910889148712},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41045185923576355}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8399934768676758},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357657194137573},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6339083909988403},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.6299346685409546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5732981562614441},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5631071925163269},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5018472671508789},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49771931767463684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4934329092502594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4726910889148712},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41045185923576355},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053163","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2004672974","https://openalex.org/W2106347453","https://openalex.org/W2137871902","https://openalex.org/W2171144711","https://openalex.org/W2400801499","https://openalex.org/W2597655663","https://openalex.org/W2726515241","https://openalex.org/W2786839803","https://openalex.org/W2798968609","https://openalex.org/W2803609229","https://openalex.org/W2891229414","https://openalex.org/W2894164357","https://openalex.org/W2896457183","https://openalex.org/W2900987791","https://openalex.org/W2901616798","https://openalex.org/W2962739339","https://openalex.org/W2963288440","https://openalex.org/W2963308316","https://openalex.org/W2963341956","https://openalex.org/W2963386218","https://openalex.org/W2964052309","https://openalex.org/W2965210982","https://openalex.org/W2970597249","https://openalex.org/W2972584841","https://openalex.org/W2973049979","https://openalex.org/W2997200074","https://openalex.org/W4297683418","https://openalex.org/W6713001283","https://openalex.org/W6735377749","https://openalex.org/W6748263443","https://openalex.org/W6748647904","https://openalex.org/W6750924170","https://openalex.org/W6751425476","https://openalex.org/W6755207826","https://openalex.org/W6756859573","https://openalex.org/W6763701032","https://openalex.org/W6766481131"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"End-to-end":[0,28],"Spoken":[1],"Language":[2],"Understanding":[3],"(SLU)":[4],"is":[5],"proposed":[6],"to":[7],"infer":[8],"the":[9,46,51,59,67],"semantic":[10,42],"meaning":[11],"directly":[12],"from":[13,34],"audio":[14],"features":[15,43],"without":[16],"intermediate":[17],"text":[18],"representation.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23],"explore":[24],"unsupervised":[25],"pre-training":[26],"for":[27],"SLU":[29,48,70],"models":[30],"by":[31],"learning":[32],"representations":[33],"large-scale":[35],"raw":[36],"audios.":[37],"The":[38],"pre-trained":[39],"model":[40,53],"preserves":[41],"which":[44],"benefit":[45],"downstream":[47],"tasks":[49],"as":[50],"learned":[52],"weights":[54],"are":[55],"further":[56],"fine-tuned":[57],"on":[58],"task":[60],"specific":[61],"training":[62],"data.":[63],"Our":[64],"approach":[65],"out-perform":[66],"state-of-the-art":[68],"end-to-end":[69],"system":[71],"with":[72],"over":[73],"18.33%":[74],"error":[75],"reduction.":[76]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}