{"id":"https://openalex.org/W2697358943","doi":"https://doi.org/10.1109/icassp.2017.7953146","title":"Effective joint training of denoising feature space transforms and Neural Network based acoustic models","display_name":"Effective joint training of denoising feature space transforms and Neural Network based acoustic models","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2697358943","doi":"https://doi.org/10.1109/icassp.2017.7953146","mag":"2697358943"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953146","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":"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/A5102876935","display_name":"Takashi Fukuda","orcid":"https://orcid.org/0000-0002-4601-0955"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Fukuda","raw_affiliation_strings":["IBM Watson Multimodal, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Multimodal, Tokyo, JAPAN","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033500018","display_name":"Osamu Ichikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Ichikawa","raw_affiliation_strings":["IBM Watson Multimodal, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Multimodal, Tokyo, JAPAN","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":["IBM Watson Multimodal, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Multimodal, Tokyo, JAPAN","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":["IBM Watson Multimodal, Tokyo, JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Multimodal, Tokyo, JAPAN","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787514","display_name":"Samuel Thomas","orcid":"https://orcid.org/0000-0001-7573-0620"},"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":"Samuel Thomas","raw_affiliation_strings":["IBM Watson Multimodal, NY, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Multimodal, NY, US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","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 Multimodal, NY, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Watson Multimodal, NY, US","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5190","last_page":"5194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.7363185882568359},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6336870193481445},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6287180185317993},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.542833685874939},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.535993218421936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5014364719390869},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5006067752838135},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49875712394714355},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.4923497438430786},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4919740855693817},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2900894284248352},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07236331701278687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363185882568359},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6336870193481445},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6287180185317993},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.542833685874939},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.535993218421936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5014364719390869},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5006067752838135},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49875712394714355},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.4923497438430786},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4919740855693817},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2900894284248352},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07236331701278687},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953146","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":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W248645961","https://openalex.org/W1517348348","https://openalex.org/W1598508708","https://openalex.org/W1904365287","https://openalex.org/W1979482308","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2028706510","https://openalex.org/W2042141988","https://openalex.org/W2062164080","https://openalex.org/W2071581583","https://openalex.org/W2076794394","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2114719288","https://openalex.org/W2115086266","https://openalex.org/W2128653836","https://openalex.org/W2135029798","https://openalex.org/W2140595311","https://openalex.org/W2140979961","https://openalex.org/W2145094598","https://openalex.org/W2290318471","https://openalex.org/W2292733088","https://openalex.org/W2394932179","https://openalex.org/W2394967684","https://openalex.org/W2400676773","https://openalex.org/W2400885515","https://openalex.org/W2402146185","https://openalex.org/W2408583661","https://openalex.org/W2408592723","https://openalex.org/W2507680812","https://openalex.org/W2514722735","https://openalex.org/W2515911524","https://openalex.org/W2916986993","https://openalex.org/W2963217176","https://openalex.org/W2963490782","https://openalex.org/W2964084166","https://openalex.org/W2997574889","https://openalex.org/W4298843173","https://openalex.org/W6630687167","https://openalex.org/W6640036494","https://openalex.org/W6677416784","https://openalex.org/W6680012447","https://openalex.org/W6681096077","https://openalex.org/W6696830301","https://openalex.org/W6712930963","https://openalex.org/W6713281174","https://openalex.org/W6843943695"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W2021595906","https://openalex.org/W2766087987","https://openalex.org/W1606020025","https://openalex.org/W2770593030","https://openalex.org/W4321487865","https://openalex.org/W3154990682","https://openalex.org/W4281727072","https://openalex.org/W4313906399","https://openalex.org/W2560201613"],"abstract_inverted_index":{"Neural":[0,83],"Network":[1,84],"(NN)":[2],"based":[3,20,68,86],"acoustic":[4,21,69,99],"frontends,":[5],"such":[6,34,59],"as":[7],"denoising":[8,61,87],"autoencoders,":[9],"are":[10],"actively":[11],"being":[12],"investigated":[13],"to":[14,23,42,56,110,147,193,201],"improve":[15,44],"the":[16,30,102,106,127,131,137,141,151,155,176,189,198],"robustness":[17],"of":[18,33,74,126,165,175,188,208],"NN":[19,67,97],"models":[22],"various":[24,72],"noise":[25],"conditions.":[26],"In":[27,48,101],"recent":[28],"work":[29],"joint":[31,138],"training":[32,125],"frontends":[35],"with":[36,71,95,130],"backend":[37,98,144],"NNs":[38],"has":[39],"been":[40],"shown":[41],"significantly":[43],"speech":[45],"recognition":[46],"performance.":[47,153,183],"this":[49,93],"paper,":[50],"we":[51],"propose":[52],"an":[53,162],"effective":[54],"algorithm":[55],"jointly":[57,91],"train":[58],"a":[60,66,81,96,169,203],"feature":[62,194],"space":[63,195],"transform":[64],"and":[65,89,143],"model":[70],"kinds":[73],"data.":[75],"Our":[76],"proposed":[77,128,159],"method":[78],"first":[79],"pretrains":[80],"Convolutional":[82],"(CNN)":[85],"frontend":[88,94,107,142,190],"then":[90],"trains":[92],"model.":[100],"unsupervised":[103],"pretraining":[104],"stage,":[105],"is":[108,168],"designed":[109],"estimate":[111],"clean":[112],"log":[113],"Mel-filterbank":[114],"features":[115],"from":[116],"noisy":[117],"log-power":[118],"spectral":[119],"input":[120],"features.":[121],"A":[122,184],"subsequent":[123],"multi-stage":[124],"frontend,":[129],"dropout":[132],"technique":[133],"applied":[134],"only":[135],"at":[136],"layer":[139],"between":[140],"NNs,":[145],"leads":[146],"significant":[148],"improvements":[149],"in":[150],"overall":[152],"On":[154],"Aurora-4":[156],"task,":[157],"our":[158],"system":[160],"achieves":[161],"average":[163,199],"WER":[164,200,206],"9.98%.":[166],"This":[167],"9.0%":[170],"relative":[171,205],"improvement":[172,207],"over":[173],"one":[174],"best":[177],"reported":[178],"speaker":[179],"independent":[180],"baseline":[181],"system's":[182],"final":[185],"semi-supervised":[186],"adaptation":[187],"NN,":[191],"similar":[192],"adaptation,":[196],"reduces":[197],"7.39%,":[202],"further":[204],"25%.":[209]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}