{"id":"https://openalex.org/W2914601236","doi":"https://doi.org/10.1109/icdsp.2018.8631862","title":"A Study on Improving Acoustic Model for Robust and Far-Field Speech Recognition","display_name":"A Study on Improving Acoustic Model for Robust and Far-Field Speech Recognition","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2914601236","doi":"https://doi.org/10.1109/icdsp.2018.8631862","mag":"2914601236"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2018.8631862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2018.8631862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","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/A5083184776","display_name":"Shaofei Xue","orcid":"https://orcid.org/0000-0001-6199-7965"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Xue","raw_affiliation_strings":["Alibaba Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Inc., Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijie Yan","raw_affiliation_strings":["Alibaba Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Inc., Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100638908","display_name":"Tao Yu","orcid":"https://orcid.org/0000-0002-2590-1513"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Yu","raw_affiliation_strings":["Alibaba Group (U.S.) Inc., Seattle, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group (U.S.) Inc., Seattle, U.S.A","institution_ids":["https://openalex.org/I4210095624","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119269608","display_name":"Zhang Liu","orcid":"https://orcid.org/0000-0001-5333-8054"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Liu","raw_affiliation_strings":["Alibaba Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Inc., Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4988,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66675357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"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/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9983999729156494,"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":0.7402640581130981},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7081775069236755},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.5736863613128662},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5587700009346008},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5061177611351013},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48581409454345703},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4496144652366638},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4473242461681366},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42083853483200073},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.41362425684928894},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4129335284233093},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3359973728656769},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19509097933769226},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1244877278804779}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402640581130981},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7081775069236755},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.5736863613128662},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5587700009346008},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5061177611351013},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48581409454345703},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4496144652366638},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4473242461681366},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42083853483200073},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.41362425684928894},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4129335284233093},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3359973728656769},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19509097933769226},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1244877278804779},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2018.8631862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2018.8631862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 23rd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1600744878","https://openalex.org/W1935589317","https://openalex.org/W2044893557","https://openalex.org/W2061074721","https://openalex.org/W2062164080","https://openalex.org/W2063521662","https://openalex.org/W2102958376","https://openalex.org/W2128402994","https://openalex.org/W2141411743","https://openalex.org/W2160815625","https://openalex.org/W2289480995","https://openalex.org/W2296167893","https://openalex.org/W2398723458","https://openalex.org/W2407277936","https://openalex.org/W2512499206","https://openalex.org/W2589857635","https://openalex.org/W2615063356","https://openalex.org/W2617258110","https://openalex.org/W2618825466","https://openalex.org/W2622203030","https://openalex.org/W2631415506","https://openalex.org/W2696967604","https://openalex.org/W2791396024","https://openalex.org/W2963308316","https://openalex.org/W2963399332","https://openalex.org/W2964084166","https://openalex.org/W6696297307","https://openalex.org/W6738603831","https://openalex.org/W6766224279"],"related_works":["https://openalex.org/W2545798066","https://openalex.org/W2385145472","https://openalex.org/W2351541234","https://openalex.org/W1969439651","https://openalex.org/W2013108665","https://openalex.org/W2259411108","https://openalex.org/W2106386991","https://openalex.org/W2966095942","https://openalex.org/W3199097733","https://openalex.org/W1955848339"],"abstract_inverted_index":{"Far-field":[0],"speech":[1,49,63,98,120],"recognition":[2,50,64,121],"is":[3,23],"an":[4],"essential":[5],"technique":[6],"for":[7,91],"man-machine":[8],"interactions.":[9],"It":[10],"aims":[11],"to":[12,16,25,70],"enable":[13],"smart":[14,30,35],"devices":[15],"recognize":[17],"distant":[18],"human":[19,80],"speech.":[20],"This":[21],"technology":[22],"applied":[24],"many":[26],"scenarios":[27],"such":[28,73],"as":[29,74],"home":[31],"appliances":[32],"(smart":[33],"loudspeaker,":[34],"TV)":[36],"and":[37,47,78,108],"meeting":[38],"transcription.":[39],"Despite":[40],"the":[41,52,61,93,126,135],"significant":[42],"advancement":[43],"made":[44],"in":[45],"robust":[46],"far-field":[48,62,97],"after":[51],"introduction":[53],"of":[54,95,128],"deep":[55],"neural":[56,109],"network":[57,110],"based":[58,111],"acoustic":[59,112],"models,":[60],"remains":[65],"a":[66],"challenging":[67],"task":[68],"due":[69],"various":[71],"factors":[72],"background":[75],"noise,":[76],"reverberation":[77],"even":[79],"voice":[81],"interference.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"describe":[87],"several":[88,117],"technical":[89,130],"advances":[90,131],"improving":[92],"performance":[94],"large-scale":[96],"recognition,":[99],"including":[100],"simulated":[101],"data":[102],"generation,":[103],"improvements":[104],"on":[105,116],"front-end":[106],"modules":[107],"models.":[113,137],"Experimental":[114],"results":[115],"Mandarin":[118],"Chinese":[119],"tasks":[122],"have":[123],"demonstrated":[124],"that":[125],"combination":[127],"these":[129],"can":[132],"significantly":[133],"outperform":[134],"conventional":[136]},"counts_by_year":[{"year":2020,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}