{"id":"https://openalex.org/W2633221078","doi":"https://doi.org/10.21437/interspeech.2017-1242","title":"An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation","display_name":"An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2633221078","doi":"https://doi.org/10.21437/interspeech.2017-1242","mag":"2633221078"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1242","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/229214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077304441","display_name":"Sibo Tong","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sibo Tong","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081808619","display_name":"Philip N. Garner","orcid":"https://orcid.org/0000-0002-0814-1348"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philip N. Garner","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077304441"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":5.6064,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.96621048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"714","last_page":"718"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9948999881744385,"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/computer-science","display_name":"Computer science","score":0.8001415729522705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6912350654602051},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6517428159713745},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.618223249912262},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5612481236457825},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045982599258423},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4995114803314209},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3629286587238312},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09683957695960999},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.05181959271430969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001415729522705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6912350654602051},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6517428159713745},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.618223249912262},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5612481236457825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045982599258423},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4995114803314209},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3629286587238312},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09683957695960999},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.05181959271430969},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2017-1242","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:229214","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/229214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:229214","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/229214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W142063520","https://openalex.org/W319941341","https://openalex.org/W1513820424","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1970890968","https://openalex.org/W1975550806","https://openalex.org/W1978660892","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2025401819","https://openalex.org/W2038810952","https://openalex.org/W2069631319","https://openalex.org/W2084534958","https://openalex.org/W2094147890","https://openalex.org/W2106440210","https://openalex.org/W2127982613","https://openalex.org/W2130414229","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2292087804","https://openalex.org/W2397721308","https://openalex.org/W2398054607","https://openalex.org/W2407240503","https://openalex.org/W2407897255","https://openalex.org/W2515572005"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W2996078371"],"abstract_inverted_index":{"Different":[0],"training":[1,75,87,144],"and":[2,24,45,70,95,117,126],"adaptation":[3,127],"techniques":[4,77],"for":[5,110],"multilingual":[6,30,62],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR)":[10],"are":[11,40,67,101],"explored":[12],"in":[13],"the":[14,33,46,124,129,134],"context":[15],"of":[16,54],"hybrid":[17],"systems,":[18],"exploiting":[19,69],"Deep":[20],"Neural":[21],"Networks":[22],"(DNN)":[23],"Hidden":[25,97],"Markov":[26],"Models":[27],"(HMM).":[28],"In":[29,103],"DNN":[31,113,156],"training,":[32],"hidden":[34],"layers":[35],"(possibly":[36],"extracting":[37],"bottleneck":[38],"features)":[39],"usually":[41],"shared":[42],"across":[43],"languages,":[44],"output":[47,108],"layer":[48,131],"can":[49],"either":[50],"model":[51],"multiple":[52],"sets":[53],"language-specific":[55],"senones":[56],"or":[57],"one":[58],"single":[59],"universal":[60,112,155],"IPA-based":[61,111,154],"senone":[63],"set.":[64],"Both":[65],"architectures":[66],"investigated,":[68],"comparing":[71],"different":[72],"language":[73,106,151],"adaptive":[74,86,107],"(LAT)":[76],"originating":[78],"from":[79],"successful":[80],"DNN-based":[81],"speaker-adaptation.":[82],"More":[83],"specifically,":[84],"speaker":[85],"methods":[88],"such":[89],"as":[90],"Cluster":[91],"Adaptive":[92],"Training":[93],"(CAT)":[94],"Learning":[96],"Unit":[98],"Contribution":[99],"(LHUC)":[100],"considered.":[102],"addition,":[104],"a":[105,150,158],"architecture":[109],"is":[114],"also":[115],"studied":[116],"tested.":[118],"Experiments":[119],"show":[120,148],"that":[121,149],"LAT":[122],"improves":[123,133],"performance":[125],"on":[128],"top":[130],"further":[132],"accuracy.":[135],"By":[136],"combining":[137],"state-level":[138],"minimum":[139],"Bayes":[140],"risk":[141],"(sMBR)":[142],"sequence":[143,160],"with":[145],"LAT,":[146],"we":[147],"adaptively":[152],"trained":[153,161],"outperforms":[157],"monolingually":[159],"model.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
