{"id":"https://openalex.org/W2716988359","doi":"https://doi.org/10.1109/icassp.2017.7953167","title":"Network architectures for multilingual speech representation learning","display_name":"Network architectures for multilingual speech representation learning","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2716988359","doi":"https://doi.org/10.1109/icassp.2017.7953167","mag":"2716988359"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5006044037","display_name":"Tom Sercu","orcid":"https://orcid.org/0000-0003-2947-6064"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tom Sercu","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101625242","display_name":"Jia Cui","orcid":"https://orcid.org/0000-0002-1631-0535"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Cui","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088302697","display_name":"Abhinav Sethy","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Sethy","raw_affiliation_strings":["IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM Watson, IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006044037"],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":2.7303,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92374927,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5295","last_page":"5299"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.8812391757965088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6077798008918762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5769572854042053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5161269903182983},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49303242564201355},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.48594534397125244},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4849557876586914},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4702804386615753},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45149725675582886},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43065375089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8812391757965088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6077798008918762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5769572854042053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5161269903182983},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49303242564201355},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.48594534397125244},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4849557876586914},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4702804386615753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45149725675582886},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43065375089645386},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953167","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953167","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":0.7400000095367432,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1499864241","https://openalex.org/W1501286448","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1987238397","https://openalex.org/W1992912377","https://openalex.org/W2064675550","https://openalex.org/W2112739286","https://openalex.org/W2123798005","https://openalex.org/W2143612262","https://openalex.org/W2155273149","https://openalex.org/W2163605009","https://openalex.org/W2198724430","https://openalex.org/W2291975472","https://openalex.org/W2394526247","https://openalex.org/W2799046698","https://openalex.org/W2949117887","https://openalex.org/W2963174142","https://openalex.org/W6629930100","https://openalex.org/W6630162575","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973","https://openalex.org/W105599799","https://openalex.org/W1483316057"],"abstract_inverted_index":{"Multilingual":[0],"(ML)":[1],"representations":[2,47,97,176],"play":[3],"a":[4,58,65,88,92,130],"key":[5],"role":[6],"in":[7,32,48,154],"building":[8,23],"speech":[9,24,158],"recognition":[10,25,159],"systems":[11,31],"for":[12,110,185],"low":[13],"resource":[14],"languages.":[15],"The":[16,40,94,114],"IARPA":[17],"sponsored":[18],"BABEL":[19,50],"program":[20,51],"focuses":[21],"on":[22,118,129,180],"(ASR)":[26],"and":[27,77,124,160,164,173],"keyword":[28,161],"search":[29,162],"(KWS)":[30],"over":[33,147],"24":[34],"languages":[35],"with":[36,54],"limited":[37],"training":[38],"data.":[39],"most":[41],"common":[42],"mechanism":[43],"to":[44,81],"derive":[45],"ML":[46,112,138,152,175],"the":[49,55,61,82,101,125,148,166,169,174,182,186],"has":[52],"been":[53],"use":[56],"of":[57,156],"two-stage":[59],"network,":[60],"first":[62,115],"stage":[63,84],"being":[64],"convolutional":[66],"network":[67],"(CNN)":[68],"from":[69,100,141,178],"where":[70],"multilingual":[71,96],"features":[72,139],"are":[73,98],"extracted,":[74],"expanded":[75],"contextually":[76],"used":[78],"as":[79],"input":[80],"second":[83,102,126],"which":[85],"can":[86],"be":[87],"feed-forward":[89],"DNN":[90],"or":[91],"CNN.":[93],"final":[95],"derived":[99,177],"network.":[103],"This":[104],"paper":[105],"presents":[106],"two":[107],"novel":[108],"methods":[109],"deriving":[111],"representations.":[113],"is":[116,127],"based":[117,128,151],"Long-Short":[119],"Term":[120],"Memory":[121],"(LSTM)":[122],"networks":[123],"very":[131],"deep":[132],"CNN":[133],"(VGG-net).":[134],"We":[135],"demonstrate":[136],"that":[137],"extracted":[140],"both":[142,157],"models":[143],"show":[144],"significant":[145],"improvement":[146],"baseline":[149],"CNN-DNN":[150],"representations,":[153],"terms":[155],"performance":[163],"draw":[165],"comparison":[167],"between":[168],"LSTM":[170],"model":[171],"itself":[172],"it":[179],"Georgian,":[181],"surprise":[183],"language":[184],"OpenKWS":[187],"evaluation.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}