{"id":"https://openalex.org/W2940131043","doi":"https://doi.org/10.1109/icassp.2019.8682403","title":"Universal Acoustic Modeling Using Neural Mixture Models","display_name":"Universal Acoustic Modeling Using Neural Mixture Models","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2940131043","doi":"https://doi.org/10.1109/icassp.2019.8682403","mag":"2940131043"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101814582","display_name":"Amit Das","orcid":"https://orcid.org/0000-0001-7733-2976"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Das","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022890229","display_name":"Changliang Liu","orcid":"https://orcid.org/0009-0005-8201-0871"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changliang Liu","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft, One Microsoft Way, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.328,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.58315969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5681","last_page":"5685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9965000152587891,"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/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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":0.7557357549667358},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6145753860473633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5494300127029419},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5376670360565186},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5285429358482361},{"id":"https://openalex.org/keywords/gating","display_name":"Gating","score":0.5126366019248962},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4581507742404938},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.43072837591171265},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4249066710472107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42226824164390564},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40975049138069153},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37504124641418457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16706398129463196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557357549667358},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6145753860473633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5494300127029419},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5376670360565186},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5285429358482361},{"id":"https://openalex.org/C194544171","wikidata":"https://www.wikidata.org/wiki/Q21105679","display_name":"Gating","level":2,"score":0.5126366019248962},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4581507742404938},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.43072837591171265},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4249066710472107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42226824164390564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40975049138069153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37504124641418457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16706398129463196},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C42407357","wikidata":"https://www.wikidata.org/wiki/Q521","display_name":"Physiology","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1513820424","https://openalex.org/W1567690964","https://openalex.org/W1593114658","https://openalex.org/W1992475611","https://openalex.org/W1995562189","https://openalex.org/W2025653905","https://openalex.org/W2043385819","https://openalex.org/W2064675550","https://openalex.org/W2069631319","https://openalex.org/W2115730999","https://openalex.org/W2119615570","https://openalex.org/W2128408412","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2150884987","https://openalex.org/W2160815625","https://openalex.org/W2213952365","https://openalex.org/W2293634267","https://openalex.org/W2396384435","https://openalex.org/W2399383297","https://openalex.org/W2402040300","https://openalex.org/W2403524927","https://openalex.org/W2575629043","https://openalex.org/W2625454625","https://openalex.org/W2735006420","https://openalex.org/W2741239878","https://openalex.org/W2775477443","https://openalex.org/W2891628540","https://openalex.org/W2939248538","https://openalex.org/W2962826786","https://openalex.org/W2962962542","https://openalex.org/W2963280294","https://openalex.org/W2963326356","https://openalex.org/W2963523217","https://openalex.org/W2963970535","https://openalex.org/W2964308564","https://openalex.org/W6623517193","https://openalex.org/W6635221813","https://openalex.org/W6676562027","https://openalex.org/W6679434410","https://openalex.org/W6688428952","https://openalex.org/W6696934422","https://openalex.org/W6712847557","https://openalex.org/W6713003356","https://openalex.org/W6713292810"],"related_works":["https://openalex.org/W2031449089","https://openalex.org/W2112596406","https://openalex.org/W2125499229","https://openalex.org/W2072696177","https://openalex.org/W4385304246","https://openalex.org/W4387096269","https://openalex.org/W4387096070","https://openalex.org/W2410610877","https://openalex.org/W2129483036","https://openalex.org/W2368671581"],"abstract_inverted_index":{"Acoustic":[0],"models":[1,42],"are":[2],"domain":[3,40],"dependent":[4],"and":[5,17,61,145],"do":[6],"not":[7],"perform":[8],"well":[9],"if":[10],"there":[11],"is":[12,52,62,111,131],"a":[13,46,137,167,196],"mismatch":[14],"between":[15],"training":[16],"test":[18,198],"conditions.":[19],"As":[20],"an":[21,187],"alternative,":[22],"the":[23,36,54,65,68,79,97,108,123,143,149,155,159,192],"Mixture":[24],"of":[25,38,64,67,92,107],"Experts":[26],"(MoE)":[27],"model":[28,87,140,165,169,189],"was":[29],"introduced":[30],"for":[31,195],"multi-domain":[32],"modeling.":[33],"It":[34],"combines":[35],"outputs":[37,91],"several":[39,75],"specific":[41],"(or":[43],"experts)":[44],"using":[45,127,170],"gating":[47,55,98,130,173],"network.":[48,99],"However,":[49],"one":[50],"drawback":[51],"that":[53,103,120,141],"network":[56],"directly":[57,121],"uses":[58,142],"raw":[59],"features":[60],"unaware":[63],"state":[66],"experts.":[69],"In":[70],"this":[71],"work,":[72],"we":[73,89,101,118,135],"propose":[74],"alternatives":[76],"to":[77,83,96,153],"improve":[78],"MoE":[80,86],"model.":[81],"First,":[82],"make":[84],"our":[85],"state-aware,":[88],"use":[90],"experts":[93],"as":[94],"inputs":[95],"Then":[100],"show":[102,119],"vector":[104],"based":[105,172],"interpolation":[106],"mixture":[109,124,146,156],"weights":[110,125,147,157],"more":[112],"effective":[113],"than":[114],"scalar":[115],"interpolation.":[116],"Second,":[117],"learning":[122],"without":[126],"any":[128],"complex":[129],"still":[132],"effective.":[133],"Finally,":[134],"introduce":[136],"hybrid":[138],"attention":[139],"logits":[144],"from":[148],"previous":[150],"time":[151],"step":[152],"generate":[154],"at":[158],"current":[160],"time.":[161],"Our":[162],"best":[163,193],"proposed":[164],"outperforms":[166],"baseline":[168],"LSTM":[171],"achieving":[174],"about":[175],"20.48%":[176],"relative":[177],"reduction":[178],"in":[179],"word":[180],"error":[181],"rate":[182],"(WER).":[183],"Moreover,":[184],"it":[185],"beats":[186],"oracle":[188],"which":[190],"picks":[191],"expert":[194],"given":[197],"condition.":[199]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}