{"id":"https://openalex.org/W2892009249","doi":"https://doi.org/10.1109/icassp.2018.8462506","title":"Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition","display_name":"Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892009249","doi":"https://doi.org/10.1109/icassp.2018.8462506","mag":"2892009249"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5000236213","display_name":"Linhao Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linhao Dong","raw_affiliation_strings":["University of Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102732438","display_name":"Shuang Xu","orcid":"https://orcid.org/0000-0003-1804-4012"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000236213"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":73.6112,"has_fulltext":false,"cited_by_count":1067,"citation_normalized_percentile":{"value":0.99926807,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5884","last_page":"5888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991000294685364,"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":0.9987999796867371,"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/transformer","display_name":"Transformer","score":0.7668718099594116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508202791213989},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7465986013412476},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7331985831260681},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6388691663742065},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.48025253415107727},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.471798837184906},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.44528618454933167},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4406237006187439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4155791997909546},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35500413179397583},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3051240146160126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20926401019096375},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09094646573066711},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08522570133209229}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7668718099594116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508202791213989},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7465986013412476},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7331985831260681},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6388691663742065},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.48025253415107727},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.471798837184906},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.44528618454933167},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4406237006187439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4155791997909546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35500413179397583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3051240146160126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20926401019096375},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09094646573066711},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08522570133209229},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462506","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462506","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1924770834","https://openalex.org/W2102113734","https://openalex.org/W2125838338","https://openalex.org/W2143612262","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2396144419","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2530876040","https://openalex.org/W2577366047","https://openalex.org/W2605141709","https://openalex.org/W2620290161","https://openalex.org/W2735006420","https://openalex.org/W2952288254","https://openalex.org/W2962826786","https://openalex.org/W2963827914","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6675365184"],"related_works":["https://openalex.org/W3203142394","https://openalex.org/W4390516098","https://openalex.org/W2161474341","https://openalex.org/W2962906565","https://openalex.org/W4298158270","https://openalex.org/W2271496879","https://openalex.org/W2102131353","https://openalex.org/W3171409398","https://openalex.org/W1968425736","https://openalex.org/W4226172942"],"abstract_inverted_index":{"Recurrent":[0],"sequence-to-sequence":[1,41,131],"models":[2],"using":[3],"encoder-decoder":[4],"architecture":[5],"have":[6],"made":[7],"great":[8],"progress":[9],"in":[10],"speech":[11,80,97],"recognition":[12,98],"task.":[13],"However,":[14],"they":[15],"suffer":[16],"from":[17],"the":[18,25,29,37,50,72,78,88,92,112,126],"drawback":[19],"of":[20,77,109,129],"slow":[21],"training":[22,30,114],"speed":[23],"because":[24],"internal":[26],"recurrence":[27],"limits":[28],"parallelization.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35],"present":[36],"Speech-Transformer,":[38],"a":[39,64],"no-recurrence":[40],"model":[42,102],"entirely":[43],"relies":[44],"on":[45,91,120],"attention":[46],"mechanisms":[47],"to":[48,71],"learn":[49],"positional":[51],"dependencies,":[52],"which":[53,67],"can":[54,68],"be":[55],"trained":[56],"faster":[57,124],"with":[58],"more":[59,84],"efficiency.":[60],"We":[61],"also":[62],"propose":[63],"2D-Attention":[65],"mechanism,":[66],"jointly":[69],"attend":[70],"time":[73],"and":[74],"frequency":[75],"axes":[76],"2-dimensional":[79],"inputs,":[81],"thus":[82],"providing":[83],"expressive":[85],"representations":[86],"for":[87],"Speech-Transformer.":[89],"Evaluated":[90],"Wall":[93],"Street":[94],"Journal":[95],"(WSJ)":[96],"dataset,":[99],"our":[100],"best":[101],"achieves":[103],"competitive":[104],"word":[105],"error":[106],"rate":[107],"(WER)":[108],"10.9%,":[110],"while":[111],"whole":[113],"process":[115],"only":[116],"takes":[117],"1.2":[118],"days":[119],"1":[121],"GPU,":[122],"significantly":[123],"than":[125],"published":[127],"results":[128],"recurrent":[130],"models.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":133},{"year":2024,"cited_by_count":139},{"year":2023,"cited_by_count":183},{"year":2022,"cited_by_count":163},{"year":2021,"cited_by_count":227},{"year":2020,"cited_by_count":148},{"year":2019,"cited_by_count":55},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}