{"id":"https://openalex.org/W2399715921","doi":"https://doi.org/10.1109/icassp.2016.7472833","title":"Machine translation based data augmentation for Cantonese keyword spotting","display_name":"Machine translation based data augmentation for Cantonese keyword spotting","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2399715921","doi":"https://doi.org/10.1109/icassp.2016.7472833","mag":"2399715921"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5072219329","display_name":"Guangpu Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Guangpu Huang","raw_affiliation_strings":["LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002166593","display_name":"Arseniy Gorin","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arseniy Gorin","raw_affiliation_strings":["LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, Orsay Cedex, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072219329"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":3.8563,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94173026,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6020","last_page":"6024"},"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":0.9991000294685364,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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":0.873720645904541},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.8129757642745972},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7621625661849976},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7535290122032166},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6841990947723389},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6691948771476746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6471878886222839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6343092918395996},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6265589594841003},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5395315289497375},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4620494246482849},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.45816972851753235},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43882161378860474},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4211137592792511},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11577478051185608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.873720645904541},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8129757642745972},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7621625661849976},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7535290122032166},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6841990947723389},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6691948771476746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6471878886222839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6343092918395996},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6265589594841003},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5395315289497375},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4620494246482849},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.45816972851753235},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43882161378860474},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4211137592792511},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11577478051185608},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472833","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W16967297","https://openalex.org/W132821814","https://openalex.org/W1420976978","https://openalex.org/W1502958118","https://openalex.org/W1565198967","https://openalex.org/W1603342183","https://openalex.org/W1904457459","https://openalex.org/W1974205368","https://openalex.org/W1992912377","https://openalex.org/W2007249154","https://openalex.org/W2080401855","https://openalex.org/W2088275353","https://openalex.org/W2094971681","https://openalex.org/W2096854399","https://openalex.org/W2105830342","https://openalex.org/W2124807415","https://openalex.org/W2141599568","https://openalex.org/W2159948109","https://openalex.org/W2251892835","https://openalex.org/W2292087804","https://openalex.org/W2398569491","https://openalex.org/W2403657120","https://openalex.org/W2407420912","https://openalex.org/W4230813784","https://openalex.org/W4253733474","https://openalex.org/W6651997312","https://openalex.org/W6680890276","https://openalex.org/W6683644788","https://openalex.org/W6691564168","https://openalex.org/W6696449567","https://openalex.org/W6713511519","https://openalex.org/W6713813099"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2114097550","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2170821097","https://openalex.org/W2069071271","https://openalex.org/W4378945174","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361"],"abstract_inverted_index":{"This":[0,87],"paper":[1],"presents":[2],"a":[3,7,11,19,39,49,70],"method":[4,88],"to":[5,22,47,57,68,94],"improve":[6],"language":[8,13,21,73],"model":[9,35,74],"for":[10,25,75,79],"limited-resourced":[12],"using":[14],"statistical":[15],"machine":[16,33],"translation":[17,34],"from":[18],"related":[20],"generate":[23],"data":[24],"the":[26,32,90],"target":[27],"language.":[28],"In":[29],"this":[30],"work,":[31],"is":[36],"trained":[37],"on":[38,106],"corpus":[40],"of":[41,52],"parallel":[42],"Mandarin-Cantonese":[43],"subtitles":[44],"and":[45,78,101],"used":[46,67],"translate":[48],"large":[50],"set":[51],"Mandarin":[53],"conversational":[54,84],"telephone":[55,85],"transcripts":[56,65],"Cantonese,":[58],"which":[59],"has":[60],"limited":[61],"resources.":[62],"The":[63],"translated":[64],"are":[66],"train":[69],"more":[71,98],"robust":[72],"speech":[76],"recognition":[77],"keyword":[80,91],"search":[81,92],"in":[82],"Cantonese":[83],"speech.":[86],"enables":[89],"system":[93],"detect":[95],"1.5":[96],"times":[97],"out-of-vocabulary":[99],"words,":[100],"achieve":[102],"1.7%":[103],"absolute":[104],"improvement":[105],"actual":[107],"term-weighted":[108],"value.":[109]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}