{"id":"https://openalex.org/W2630683241","doi":"https://doi.org/10.1109/icassp.2017.7953151","title":"Speech recognition in unseen and noisy channel conditions","display_name":"Speech recognition in unseen and noisy channel conditions","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2630683241","doi":"https://doi.org/10.1109/icassp.2017.7953151","mag":"2630683241"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953151","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/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112857367","display_name":"Horacio Franco","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Horacio Franco","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031137004","display_name":"Chris Bartels","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Bartels","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058481276","display_name":"Julien van Hout","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julien van Hout","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025265147","display_name":"Martin Graciarena","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Graciarena","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitra Vergyri","raw_affiliation_strings":["SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International, Speech Technology and Research Laboratory, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":0.969,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80235227,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5215","last_page":"5219"},"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.7775629162788391},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6693452000617981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5964076519012451},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5823490619659424},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5624334812164307},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5580344200134277},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5386865139007568},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5137806534767151},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4779531955718994},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.45528870820999146},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.45478594303131104},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4336387813091278},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.39307692646980286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36725854873657227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7775629162788391},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6693452000617981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964076519012451},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5823490619659424},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5624334812164307},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5580344200134277},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5386865139007568},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5137806534767151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4779531955718994},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.45528870820999146},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.45478594303131104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4336387813091278},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.39307692646980286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36725854873657227},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953151","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953151","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1631260214","https://openalex.org/W1970088388","https://openalex.org/W1984570643","https://openalex.org/W1989549063","https://openalex.org/W1993882792","https://openalex.org/W2034304679","https://openalex.org/W2079623482","https://openalex.org/W2140979961","https://openalex.org/W2160815625","https://openalex.org/W2162042984","https://openalex.org/W2288371874","https://openalex.org/W2288817436","https://openalex.org/W2289394825","https://openalex.org/W2289912446","https://openalex.org/W2394932179","https://openalex.org/W2395321025","https://openalex.org/W2397152345","https://openalex.org/W2398826216","https://openalex.org/W2404382759","https://openalex.org/W2404620314","https://openalex.org/W2406171445","https://openalex.org/W2407204023","https://openalex.org/W2517478361","https://openalex.org/W2887979278","https://openalex.org/W2964076070","https://openalex.org/W6636811518","https://openalex.org/W6684010798","https://openalex.org/W6712234020","https://openalex.org/W6712454336","https://openalex.org/W6712560600","https://openalex.org/W6713360458","https://openalex.org/W6713419400","https://openalex.org/W6714125293","https://openalex.org/W6753916174"],"related_works":["https://openalex.org/W2159052453","https://openalex.org/W3013693939","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,21,172],"in":[2,164,174],"varying":[3],"background":[4],"conditions":[5],"is":[6,56,65,70],"a":[7],"challenging":[8],"problem.":[9],"Acoustic":[10],"condition":[11],"mismatch":[12],"between":[13],"training":[14],"and":[15,76,94,105,177],"evaluation":[16],"data":[17,43,151],"can":[18,146],"significantly":[19,167],"reduce":[20],"performance.":[22],"For":[23],"mismatched":[24],"conditions,":[25],"data-adaptation":[26],"techniques":[27,47,78,162],"are":[28,79],"typically":[29,80],"found":[30],"to":[31,40,98,149],"be":[32,147],"useful,":[33],"as":[34],"they":[35,145],"expose":[36],"the":[37,41,100,110,129,161],"acoustic":[38,125],"model":[39,155],"new":[42],"condition(s).":[44],"Supervised":[45],"adaptation":[46],"usually":[48],"provide":[49],"substantial":[50],"performance":[51,169],"improvement,":[52],"but":[53,142],"such":[54,135],"gain":[55],"contingent":[57],"on":[58],"having":[59],"labeled":[60],"or":[61],"transcribed":[62],"data,":[63],"which":[64],"often":[66],"unavailable.":[67],"The":[68],"alternative":[69],"unsupervised":[71,154],"adaptation,":[72],"where":[73],"feature-transform":[74],"methods":[75],"model-adaptation":[77],"explored.":[81],"This":[82],"work":[83,111],"investigates":[84,112],"robust":[85,140],"features,":[86],"feature-space":[87],"maximum":[88],"likelihood":[89],"linear":[90],"regression":[91],"(fMLLR)":[92],"transform,":[93],"deep":[95,118],"convolutional":[96],"nets":[97],"address":[99],"problem":[101],"of":[102,170],"unseen":[103,175],"channel":[104,176],"noise":[106,178],"conditions.":[107,179],"In":[108],"addition,":[109],"bottleneck":[113],"(BN)":[114],"features":[115,126],"extracted":[116,127],"from":[117,128],"autoencoder":[119],"(DAE)":[120],"networks":[121],"trained":[122],"by":[123],"using":[124],"speech":[130,171],"signal.":[131],"We":[132],"demonstrate":[133],"that":[134,144,160],"representations":[136],"not":[137],"only":[138],"produce":[139],"systems":[141,173],"also":[143],"used":[148],"perform":[150],"selection":[152],"for":[153],"adaptation.":[156],"Our":[157],"results":[158],"indicate":[159],"presented":[163],"this":[165],"paper":[166],"improve":[168]},"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":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}