{"id":"https://openalex.org/W2804758356","doi":"https://doi.org/10.1109/icassp.2018.8462452","title":"Adversarial Learning of Raw Speech Features for Domain Invariant Speech Recognition","display_name":"Adversarial Learning of Raw Speech Features for Domain Invariant Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2804758356","doi":"https://doi.org/10.1109/icassp.2018.8462452","mag":"2804758356"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.08615","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019078651","display_name":"Aditay Tripathi","orcid":"https://orcid.org/0000-0002-1667-9623"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditay Tripathi","raw_affiliation_strings":["Indraprastha Institute of Information Technology, New Delhi, India","Indraprastha Institute of Information Technology, New Delhi, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, New Delhi, India","institution_ids":["https://openalex.org/I119939252"]},{"raw_affiliation_string":"Indraprastha Institute of Information Technology, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036974323","display_name":"Aanchan Mohan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112936","display_name":"Verisk Analytics (United States)","ror":"https://ror.org/01xdzbt45","country_code":"US","type":"company","lineage":["https://openalex.org/I4210112936"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aanchan Mohan","raw_affiliation_strings":["Verisk Analytics, Jersey, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Verisk Analytics, Jersey, USA","institution_ids":["https://openalex.org/I4210112936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101551646","display_name":"Saket Anand","orcid":"https://orcid.org/0000-0002-6229-3940"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Saket Anand","raw_affiliation_strings":["Indraprastha Institute of Information Technology, New Delhi, India","Indraprastha Institute of Information Technology, New Delhi, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Information Technology, New Delhi, India","institution_ids":["https://openalex.org/I119939252"]},{"raw_affiliation_string":"Indraprastha Institute of Information Technology, New Delhi, India#TAB#","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107940970","display_name":"Maneesh Singh","orcid":"https://orcid.org/0000-0002-7414-1813"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maneesh Singh","raw_affiliation_strings":["Synaptitude Brain Health, Vancouver, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Synaptitude Brain Health, Vancouver, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05489789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5959","last_page":"5963"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9958999752998352,"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":0.7641473412513733},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.7565891146659851},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6584099531173706},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5774683952331543},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5569865703582764},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5530126690864563},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.5216134786605835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5114623308181763},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47447043657302856},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4538681209087372},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4028806984424591},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3103695511817932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09562665224075317},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08050593733787537}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641473412513733},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7565891146659851},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6584099531173706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5774683952331543},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5569865703582764},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5530126690864563},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.5216134786605835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5114623308181763},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47447043657302856},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4538681209087372},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4028806984424591},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3103695511817932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09562665224075317},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08050593733787537},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2018.8462452","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.08615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.08615","pdf_url":"https://arxiv.org/pdf/1805.08615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2804758356","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1805.08615.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1805.08615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.08615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.08615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.08615","pdf_url":"https://arxiv.org/pdf/1805.08615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2804758356.pdf","grobid_xml":"https://content.openalex.org/works/W2804758356.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1616590059","https://openalex.org/W1666984270","https://openalex.org/W1731081199","https://openalex.org/W1989549063","https://openalex.org/W2015633636","https://openalex.org/W2042281066","https://openalex.org/W2094147890","https://openalex.org/W2101066392","https://openalex.org/W2142416747","https://openalex.org/W2168249605","https://openalex.org/W2168961642","https://openalex.org/W2398826216","https://openalex.org/W2508048623","https://openalex.org/W2510867321","https://openalex.org/W2584667682","https://openalex.org/W2587088898","https://openalex.org/W2749424389","https://openalex.org/W2963175699","https://openalex.org/W2963364041","https://openalex.org/W4205130185","https://openalex.org/W6604254268","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6636362120","https://openalex.org/W6637061625","https://openalex.org/W6637618735","https://openalex.org/W6678409544"],"related_works":["https://openalex.org/W2962995362","https://openalex.org/W2584667682","https://openalex.org/W2787133659","https://openalex.org/W2938486422","https://openalex.org/W2935938411","https://openalex.org/W3023508416","https://openalex.org/W2890351244","https://openalex.org/W2737108017","https://openalex.org/W3011500442","https://openalex.org/W2793646841","https://openalex.org/W3133917823","https://openalex.org/W3132220150","https://openalex.org/W3163829335","https://openalex.org/W2963057973","https://openalex.org/W3099628266","https://openalex.org/W2962909949","https://openalex.org/W2777114772","https://openalex.org/W2586425531","https://openalex.org/W1490506669","https://openalex.org/W2826003142"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,12,74,81,145,163],"neural":[3],"network":[4,106],"based":[5],"acoustic":[6,21,29,62,65],"modelling":[7],"have":[8],"shown":[9],"significant":[10],"improvements":[11],"automatic":[13],"speech":[14,57],"recognition":[15],"(ASR)":[16],"performance.":[17],"In":[18],"order":[19],"for":[20,159],"models":[22],"to":[23,26,42,52,61,69,119,143,171],"be":[24],"able":[25],"handle":[27],"large":[28,31],"variability,":[30],"amounts":[32],"of":[33,49,87,109,131,156,169],"labeled":[34],"data":[35,96],"is":[36,67,103,117,133],"necessary,":[37],"which":[38,94],"are":[39,59],"often":[40],"expensive":[41],"obtain.":[43],"This":[44,64],"paper":[45,83],"explores":[46],"the":[47,85,154,167],"application":[48],"adversarial":[50,157],"training":[51,158],"learn":[53,172],"features":[54,175],"from":[55,97,176],"raw":[56,177],"that":[58,107,116],"invariant":[60,174],"variability.":[63],"variability":[66],"referred":[68],"as":[70],"a":[71,104,110,120,125],"domain":[72,127,139,161,173],"shift":[73],"this":[75,82],"paper.":[76],"The":[77,101,129],"experimental":[78],"study":[79],"presented":[80],"leverages":[84],"architecture":[86],"Domain":[88],"Adversarial":[89],"Neural":[90],"Networks":[91],"(DANNs)":[92],"[1]":[93],"uses":[95],"two":[98],"different":[99],"domains.":[100],"DANN":[102],"Y-shaped":[105],"consists":[108],"multi-layer":[111],"CNN":[112],"feature":[113],"extractor":[114],"module":[115],"common":[118],"label":[121],"(senone)":[122],"classifier":[123],"and":[124,147],"so-called":[126],"classifier.":[128],"utility":[130],"DANNs":[132,170],"evaluated":[134],"on":[135],"multiple":[136],"datasets":[137],"with":[138],"shifts":[140],"caused":[141],"due":[142],"differences":[144],"gender":[146],"speaker":[148],"accents.":[149],"Promising":[150],"empirical":[151],"results":[152],"indicate":[153],"strength":[155],"unsupervised":[160],"adaptation":[162],"ASR,":[164],"thereby":[165],"emphasizing":[166],"ability":[168],"speech.":[178]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}