{"id":"https://openalex.org/W3007904524","doi":"https://doi.org/10.1109/asru46091.2019.9003755","title":"Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks","display_name":"Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007904524","doi":"https://doi.org/10.1109/asru46091.2019.9003755","mag":"3007904524"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003755","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036100026","display_name":"Salil Deena","orcid":"https://orcid.org/0000-0001-5417-0556"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Salil Deena","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113981675","display_name":"Md Asif Jalal","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Md Asif Jalal","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044770590","display_name":"Rasa Lileikyt\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rasa Lileikyte","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, UK"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030912143"],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":0.4201,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72762923,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"40","issue":null,"first_page":"980","last_page":"987"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9980999827384949,"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/timit","display_name":"TIMIT","score":0.8799675703048706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8090662956237793},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.8064172267913818},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6942641735076904},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6665815114974976},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5942466259002686},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5843955278396606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5461283326148987},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4466601610183716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41898036003112793},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.40339815616607666}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8799675703048706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8090662956237793},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.8064172267913818},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6942641735076904},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6665815114974976},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5942466259002686},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5843955278396606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5461283326148987},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4466601610183716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41898036003112793},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.40339815616607666},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003755","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1567690964","https://openalex.org/W1882958252","https://openalex.org/W1985371235","https://openalex.org/W1989549063","https://openalex.org/W2010362084","https://openalex.org/W2048526313","https://openalex.org/W2112021726","https://openalex.org/W2150769028","https://openalex.org/W2155648385","https://openalex.org/W2239847623","https://openalex.org/W2258198666","https://openalex.org/W2276408190","https://openalex.org/W2295119550","https://openalex.org/W2316560407","https://openalex.org/W2398776621","https://openalex.org/W2403307129","https://openalex.org/W2510867321","https://openalex.org/W2515753980","https://openalex.org/W2584667682","https://openalex.org/W2742004888","https://openalex.org/W2752782242","https://openalex.org/W2760103357","https://openalex.org/W2791636785","https://openalex.org/W2794209590","https://openalex.org/W2794506738","https://openalex.org/W2794588495","https://openalex.org/W2796339975","https://openalex.org/W2797187289","https://openalex.org/W2799674897","https://openalex.org/W2826003142","https://openalex.org/W2889519245","https://openalex.org/W2891756742","https://openalex.org/W2939173691","https://openalex.org/W2963032538","https://openalex.org/W2963235055","https://openalex.org/W2963266252","https://openalex.org/W2963288281","https://openalex.org/W2963381607","https://openalex.org/W2963403868","https://openalex.org/W2963596039","https://openalex.org/W2963826681","https://openalex.org/W2963917611","https://openalex.org/W2964227577","https://openalex.org/W3104245447","https://openalex.org/W3104896896","https://openalex.org/W3105315310","https://openalex.org/W3125118953","https://openalex.org/W3127686677","https://openalex.org/W4293495374","https://openalex.org/W4385245566","https://openalex.org/W6603403951","https://openalex.org/W6631362777","https://openalex.org/W6639480849","https://openalex.org/W6732862412","https://openalex.org/W6742082877","https://openalex.org/W6750800043","https://openalex.org/W6752004172","https://openalex.org/W6761643694"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W1694601526","https://openalex.org/W128188896"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"the":[3,27,67,95,118,129,143,167,171,179],"adaptation":[4],"of":[5,63,72,153,169],"neural":[6],"network-based":[7],"acoustic":[8,35,121,184,191],"models":[9,185],"using":[10,39,170],"a":[11],"Squeeze-and-Excitation":[12],"(SE)":[13],"network":[14,29,181],"for":[15,157,186],"automatic":[16],"speech":[17],"recognition":[18],"(ASR).":[19],"In":[20],"particular,":[21],"this":[22],"work":[23],"explores":[24],"to":[25,30,59,88,93,112,146,182],"use":[26],"SE":[28,180],"learn":[31],"utterance-level":[32,114],"embeddings.":[33],"The":[34,45,70,101,135],"modelling":[36],"is":[37,75],"performed":[38],"Light":[40],"Gated":[41],"Recurrent":[42],"Units":[43],"(LiGRU).":[44],"utterance":[46,176],"embed-dings":[47],"are":[48,107],"learned":[49,174],"from":[50],"hidden":[51,64,110],"unit":[52],"activations":[53,62],"jointly":[54],"with":[55,150],"LiGRU":[56,68],"and":[57,86,104,120,131,155,159,189],"used":[58],"scale":[60],"respective":[61,148],"layers":[65],"in":[66,91,178],"network.":[69],"advantage":[71],"such":[73,83],"approach":[74],"that":[76,116],"it":[77],"does":[78],"not":[79],"require":[80],"domain":[81],"labels,":[82],"as":[84],"speakers":[85,119],"noise":[87],"be":[89],"known":[90],"order":[92],"perform":[94],"adaptation,":[96],"thereby":[97],"providing":[98],"unsupervised":[99],"adaptation.":[100],"global":[102],"average":[103],"attentive":[105],"pooling":[106],"applied":[108],"on":[109,128,141],"units":[111],"extract":[113],"information":[115,173],"represents":[117],"conditions.":[122,192],"ASR":[123],"experiments":[124,165],"were":[125],"carried":[126],"out":[127],"TIMIT":[130,158],"Aurora":[132,160],"4":[133,161],"corpora.":[134],"proposed":[136],"model":[137],"achieves":[138],"better":[139],"performance":[140],"both":[142],"datasets":[144],"compared":[145],"their":[147],"baselines":[149],"relative":[151],"improvements":[152],"5.59%":[154],"5.54%":[156],"database,":[162],"respectively.":[163],"These":[164],"show":[166],"potential":[168],"conditioning":[172],"via":[175],"embeddings":[177],"adapt":[183],"speakers,":[187],"noise,":[188],"other":[190]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}