{"id":"https://openalex.org/W2295627154","doi":"https://doi.org/10.21437/interspeech.2015-708","title":"Large-scale, sequence-discriminative, joint adaptive training for masking-based robust ASR","display_name":"Large-scale, sequence-discriminative, joint adaptive training for masking-based robust ASR","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2295627154","doi":"https://doi.org/10.21437/interspeech.2015-708","mag":"2295627154"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-708","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":true,"raw_author_name":"Arun Narayanan","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091715883","display_name":"Ananya Misra","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":"Ananya Misra","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058000820","display_name":"K. K. Chin","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":"Kean K. Chin","raw_affiliation_strings":["Google,,,,,"],"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000078382"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":1.1487,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80187744,"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":"3571","last_page":"3575"},"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":0.9998999834060669,"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":0.9987000226974487,"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/discriminative-model","display_name":"Discriminative model","score":0.87699955701828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7987432479858398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6193593144416809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5960208177566528},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5822479724884033},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5586233139038086},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5141737461090088},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4860380291938782},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.455615371465683},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0854276716709137}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.87699955701828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7987432479858398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6193593144416809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5960208177566528},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5822479724884033},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5586233139038086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5141737461090088},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4860380291938782},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.455615371465683},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0854276716709137},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2015-708","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-708","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1599512239","https://openalex.org/W1600744878","https://openalex.org/W1831449718","https://openalex.org/W1969851134","https://openalex.org/W1974387177","https://openalex.org/W1993409002","https://openalex.org/W2031647436","https://openalex.org/W2035576074","https://openalex.org/W2042141988","https://openalex.org/W2046869671","https://openalex.org/W2055611715","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2067117291","https://openalex.org/W2086139506","https://openalex.org/W2114016253","https://openalex.org/W2117678320","https://openalex.org/W2140595311","https://openalex.org/W2168231600","https://openalex.org/W2184045248","https://openalex.org/W2293009711","https://openalex.org/W2293634267","https://openalex.org/W2328757576","https://openalex.org/W2402268235","https://openalex.org/W2405589348","https://openalex.org/W2964138484"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"Recently,":[0],"it":[1],"was":[2,59],"shown":[3],"that":[4,126],"the":[5,25,97],"performance":[6],"of":[7,99],"supervised":[8],"timefrequency":[9],"masking":[10],"based":[11,37,87],"robust":[12],"automatic":[13],"speech":[14],"recognition":[15],"techniques":[16],"can":[17,130],"be":[18],"improved":[19],"by":[20],"training":[21,64,111,129],"them":[22],"jointly":[23,75],"with":[24],"acoustic":[26,53,164],"model":[27],"[1].":[28],"The":[29],"system":[30],"in":[31,78],"[1],":[32],"termed":[33],"deep":[34,44],"neural":[35,45,85],"network":[36],"joint":[38,103,127],"adaptive":[39,128],"training,":[40],"used":[41,60],"fully-connected":[42],"feedforward":[43],"networks":[46,86],"for":[47,52,113],"estimating":[48],"time-frequency":[49],"masks":[50],"and":[51,63,124],"modeling;":[54],"stacked":[55],"log":[56],"mel":[57],"spectra":[58],"as":[61],"features":[62],"minimized":[65],"cross":[66],"entropy":[67],"loss.":[68],"In":[69],"this":[70,95],"work,":[71],"we":[72,82,106,117],"extend":[73],"such":[74],"trained":[76,162],"systems":[77],"several":[79],"ways.":[80],"First,":[81],"use":[83,98,107],"recurrent":[84],"on":[88,120,139],"long":[89],"short-term":[90],"memory":[91],"(LSTM)":[92],"units":[93],"\u2013":[94],"allows":[96],"unstacked":[100],"features,":[101],"simplifying":[102],"optimization.":[104],"Next,":[105],"a":[108,134,158],"sequence":[109,159],"discriminative":[110],"criterion":[112],"optimizing":[114],"parameters.":[115],"Finally,":[116],"conduct":[118],"experiments":[119],"large":[121],"scale":[122],"data":[123,142],"show":[125,143],"provide":[131],"gains":[132],"over":[133,157],"strong":[135],"baseline.":[136],"Systematic":[137],"evaluations":[138],"noisy":[140],"voice-search":[141],"relative":[144],"improvements":[145],"ranging":[146],"from":[147],"2%":[148],"at":[149,154],"15":[150],"dB":[151,156],"to":[152],"5.4%":[153],"-5":[155],"discriminative,":[160],"multi-condition":[161],"LSTM":[163],"model.":[165]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}