{"id":"https://openalex.org/W1986184096","doi":"https://doi.org/10.1109/icassp.2014.6854675","title":"GMM-free DNN acoustic model training","display_name":"GMM-free DNN acoustic model training","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1986184096","doi":"https://doi.org/10.1109/icassp.2014.6854675","mag":"1986184096"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":["Google Inc., New York","Google Inc., New York, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071956319","display_name":"Georg Heigold","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georg Heigold","raw_affiliation_strings":["Google Inc., New York","Google Inc., New York, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Inc., New York","Google Inc., New York, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110698977","display_name":"Hank Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hank Liao","raw_affiliation_strings":["Google Inc., New York","Google Inc., New York, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., New York","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc., New York, NY, USA#TAB#","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5602","last_page":"5606"},"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":0.9994999766349792,"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":0.9994000196456909,"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/mixture-model","display_name":"Mixture model","score":0.8760074377059937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7597377300262451},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.6450334191322327},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5915831327438354},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5911816954612732},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5726980566978455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367172360420227},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5301956534385681},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5185235738754272},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4834462106227875},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46435001492500305},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32471203804016113},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.16415759921073914},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09647944569587708}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8760074377059937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597377300262451},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.6450334191322327},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5915831327438354},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5911816954612732},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5726980566978455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367172360420227},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5301956534385681},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5185235738754272},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4834462106227875},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46435001492500305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32471203804016113},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.16415759921073914},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09647944569587708},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1994167387","https://openalex.org/W2035424729","https://openalex.org/W2049633694","https://openalex.org/W2080209778","https://openalex.org/W2105099419","https://openalex.org/W2106051978","https://openalex.org/W2114016253","https://openalex.org/W2126002878","https://openalex.org/W2137644731","https://openalex.org/W2155273149","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2184045248","https://openalex.org/W2296748324","https://openalex.org/W3129711340","https://openalex.org/W6648872938"],"related_works":["https://openalex.org/W1534274833","https://openalex.org/W3117246195","https://openalex.org/W156620619","https://openalex.org/W2098233217","https://openalex.org/W2914363205","https://openalex.org/W2616249226","https://openalex.org/W2997844990","https://openalex.org/W1598221548","https://openalex.org/W2081850291","https://openalex.org/W2735380212"],"abstract_inverted_index":{"While":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"have":[5],"become":[6],"the":[7,64,83,90,97],"dominant":[8],"acoustic":[9,92],"model":[10,66,93],"(AM)":[11],"for":[12,25,28,32],"speech":[13],"recognition":[14],"systems,":[15],"they":[16],"are":[17,60],"still":[18],"dependent":[19,34],"on":[20],"Gaussian":[21],"mixture":[22],"models":[23,80],"(GMMs)":[24],"alignments":[26,58,76,85],"both":[27],"supervised":[29],"training":[30,44],"and":[31,48,67,75,86],"context":[33],"(CD)":[35],"tree":[36],"building.":[37],"Here":[38],"we":[39,95],"explore":[40],"bootstrapping":[41],"DNN":[42,57,65,103],"AM":[43],"without":[45],"GMM":[46,84,91],"AMs":[47],"show":[49,71],"that":[50,72],"CD":[51],"trees":[52,74],"can":[53],"be":[54],"built":[55],"with":[56],"which":[59],"better":[61,79],"matched":[62],"to":[63,100],"its":[68],"features.":[69],"We":[70],"these":[73],"result":[77],"in":[78],"than":[81],"from":[82,104],"trees.":[87],"By":[88],"removing":[89],"altogether":[94],"simplify":[96],"system":[98],"required":[99],"train":[101],"a":[102],"scratch.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}