{"id":"https://openalex.org/W4372265871","doi":"https://doi.org/10.1109/icassp49357.2023.10095090","title":"M<sup>3</sup>ST: Mix at Three Levels for Speech Translation","display_name":"M<sup>3</sup>ST: Mix at Three Levels for Speech Translation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372265871","doi":"https://doi.org/10.1109/icassp49357.2023.10095090"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095090","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/A5101456600","display_name":"Xuxin Cheng","orcid":"https://orcid.org/0000-0003-2995-9349"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuxin Cheng","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,China","ADSPLAB, School of ECE, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674914","display_name":"Qianqian Dong","orcid":"https://orcid.org/0009-0001-7001-7583"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianqian Dong","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069891577","display_name":"Fengpeng Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengpeng Yue","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693712","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0000-9738-4263"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,ADSPLAB, School of ECE,China","ADSPLAB, School of ECE, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Peking University,ADSPLAB, School of ECE,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"ADSPLAB, School of ECE, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101456600"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.2238,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82717223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.763335108757019},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5827347636222839},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5695868134498596},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5683968663215637},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5683727264404297},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5588029026985168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.555198073387146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5401789546012878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5058295726776123},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4664190709590912},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4499751031398773},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1324470043182373},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0769507884979248}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.763335108757019},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5827347636222839},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5695868134498596},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5683968663215637},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5683727264404297},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5588029026985168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.555198073387146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5401789546012878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5058295726776123},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4664190709590912},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4499751031398773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1324470043182373},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0769507884979248},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095090","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095090","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W2148708890","https://openalex.org/W2419539795","https://openalex.org/W2747874407","https://openalex.org/W2765407302","https://openalex.org/W2963250244","https://openalex.org/W3015440307","https://openalex.org/W3017454464","https://openalex.org/W3118578889","https://openalex.org/W3162471442","https://openalex.org/W3163839574","https://openalex.org/W3176382501","https://openalex.org/W3176455679","https://openalex.org/W3196833881","https://openalex.org/W3209059054","https://openalex.org/W4206468798","https://openalex.org/W4221163209","https://openalex.org/W4226212120","https://openalex.org/W4281982771","https://openalex.org/W4285215858","https://openalex.org/W4287890956","https://openalex.org/W4385245566","https://openalex.org/W4385823111","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6682026795","https://openalex.org/W6717262007","https://openalex.org/W6739901393","https://openalex.org/W6745136726","https://openalex.org/W6784050962","https://openalex.org/W6810686556","https://openalex.org/W6839510803"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W3208095355","https://openalex.org/W2177370417","https://openalex.org/W2375873920","https://openalex.org/W2052507016","https://openalex.org/W3151736118","https://openalex.org/W2180461068","https://openalex.org/W2051816080","https://openalex.org/W2883671469","https://openalex.org/W2728761353"],"abstract_inverted_index":{"How":[0],"to":[1,22,50,128,136],"solve":[2],"the":[3,30,52,55,78,85,101,108,126,130],"data":[4,16],"scarcity":[5],"problem":[6],"for":[7,25,41],"end-to-end":[8],"speech-to-text":[9],"translation":[10,74,144],"(ST)?":[11],"It\u2019s":[12],"well":[13],"known":[14],"that":[15],"augmentation":[17],"is":[18],"an":[19,166],"efficient":[20],"method":[21,49],"improve":[23],"performance":[24],"many":[26],"tasks":[27],"by":[28],"enlarging":[29],"dataset.":[31],"In":[32,77],"this":[33],"paper,":[34],"we":[35,60,83,113],"propose":[36],"Mix":[37],"at":[38,88],"three":[39,89],"levels":[40],"Speech":[42],"Translation":[43],"(M":[44],"<sup":[45,150],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[46,151],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>":[47,152],"ST)":[48],"increase":[51],"diversity":[53],"of":[54,64,81,111,169],"augmented":[56],"training":[57,86],"corpus.":[58],"Specifically,":[59],"conduct":[61],"two":[62],"phases":[63],"fine-tuning":[65],"based":[66],"on":[67,141,162],"a":[68],"pre-trained":[69],"model":[70,103,127],"using":[71],"external":[72],"machine":[73],"(MT)":[75],"data.":[76,106],"first":[79],"stage":[80,110],"fine-tuning,":[82,112],"mix":[84],"corpus":[87],"levels,":[90],"including":[91],"word":[92],"level,":[93,98],"sentence":[94],"level":[95],"and":[96,99,119,132,146,158],"frame":[97],"fine-tune":[100,129],"entire":[102],"with":[104,165],"mixed":[105],"At":[107],"second":[109],"take":[114],"both":[115],"original":[116,120],"speech":[117,143],"sequences":[118,122],"text":[121],"in":[123],"parallel":[124],"into":[125],"network,":[131],"use":[133],"Jensen-Shannon":[134],"divergence":[135],"regularize":[137],"their":[138],"outputs.":[139],"Experiments":[140],"MuST-C":[142],"benchmark":[145],"analysis":[147],"show":[148],"M":[149],"ST":[153],"outperforms":[154],"current":[155],"strong":[156],"baselines":[157],"achieves":[159],"state-of-the-art":[160],"results":[161],"eight":[163],"directions":[164],"average":[167],"BLEU":[168],"29.9.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}