{"id":"https://openalex.org/W1502652411","doi":"https://doi.org/10.1109/icassp.2015.7178927","title":"Generative modeling of pseudo-target domain adaptation samples for whispered speech recognition","display_name":"Generative modeling of pseudo-target domain adaptation samples for whispered speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1502652411","doi":"https://doi.org/10.1109/icassp.2015.7178927","mag":"1502652411"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178927","doi":"https://doi.org/10.1109/icassp.2015.7178927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178927","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"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/A5040866561","display_name":"Shabnam Ghaffarzadegan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shabnam Ghaffarzadegan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009895165","display_name":"Hynek Bo\u0159il","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hynek Boril","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering, University of Texas at Dallas, Richardson, U.S.A","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.0658,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88971218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5024","last_page":"5028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.00019999999494757503,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/denoising-autoencoder","display_name":"denoising autoencoder","score":0.9810000061988831},{"id":"https://openalex.org/keywords/vector-taylor-series","display_name":"vector Taylor series","score":0.9200000166893005},{"id":"https://openalex.org/keywords/word-error-rate-reduction","display_name":"word error rate reduction","score":0.7990000247955322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.806343674659729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7198623418807983},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6394335627555847},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5587575435638428},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4905771315097809},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4683957099914551},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4422706663608551},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4389336407184601},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.43392619490623474},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4230846166610718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3861531615257263},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.34672683477401733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.250663697719574},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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.2015.7178927","doi":"https://doi.org/10.1109/icassp.2015.7178927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178927","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W5014987","https://openalex.org/W41355022","https://openalex.org/W96541173","https://openalex.org/W1973681148","https://openalex.org/W2006046472","https://openalex.org/W2021512166","https://openalex.org/W2022047569","https://openalex.org/W2025768430","https://openalex.org/W2045956438","https://openalex.org/W2055589033","https://openalex.org/W2088067539","https://openalex.org/W2095067775","https://openalex.org/W2100103540","https://openalex.org/W2106119541","https://openalex.org/W2106790438","https://openalex.org/W2117486215","https://openalex.org/W2126597753","https://openalex.org/W2142691710","https://openalex.org/W2145094598","https://openalex.org/W2146618065","https://openalex.org/W2294831733","https://openalex.org/W2296581541","https://openalex.org/W2303272654","https://openalex.org/W2395633578","https://openalex.org/W2397098974","https://openalex.org/W2997574889"],"related_works":["https://openalex.org/W2437658533","https://openalex.org/W2294831733","https://openalex.org/W2767064007","https://openalex.org/W2565286512","https://openalex.org/W2768731046","https://openalex.org/W3102538494","https://openalex.org/W4318752101","https://openalex.org/W4391021791","https://openalex.org/W2996797022","https://openalex.org/W2055589033"],"abstract_inverted_index":{"The":[0,63,145],"lack":[1],"of":[2,6,12,18,41,46,54,83,93,115,131],"available":[3],"large":[4,52],"corpora":[5],"transcribed":[7,60],"whispered":[8,48],"speech":[9],"is":[10,120],"one":[11,99],"the":[13,81,123,132,138,152],"major":[14],"roadblocks":[15],"for":[16,87],"development":[17],"successful":[19],"whisper":[20,143],"recognition":[21],"engines.":[22],"Our":[23,77],"recent":[24],"study":[25,79],"has":[26],"introduced":[27],"a":[28,43,72,106],"Vector":[29],"Taylor":[30],"Series":[31],"(VTS)":[32],"approach":[33,125,147],"to":[34,50,75,151],"pseudo-whisper":[35,64,88,113],"sample":[36,89],"generation":[37],"which":[38,100,111],"requires":[39],"availability":[40],"only":[42],"small":[44],"number":[45],"real":[47,142],"utterances":[49],"produce":[51],"amounts":[53],"whisper-like":[55],"samples":[56,65],"from":[57],"easily":[58],"accessible":[59],"neutral":[61],"recordings.":[62],"were":[66],"found":[67],"particularly":[68],"effective":[69],"in":[70,161],"adapting":[71],"neutral-trained":[73],"recognizer":[74],"whisper.":[76],"current":[78],"explores":[80],"use":[82],"denoising":[84],"autoencoders":[85],"(DAE)":[86],"generation.":[90],"Two":[91],"types":[92],"generative":[94],"models":[95],"are":[96],"investigated":[97],"-":[98],"produces":[101],"pseudo-whispered":[102],"cepstral":[103],"vectors":[104],"on":[105,141],"frame":[107],"basis":[108],"and":[109],"another":[110],"generates":[112],"statistics":[114],"whole":[116],"phone":[117],"segments.":[118],"It":[119],"shown":[121],"that":[122],"DAE":[124,146],"considerably":[126],"reduces":[127],"word":[128],"error":[129],"rates":[130],"baseline":[133],"system":[134,139],"as":[135,137],"well":[136],"adapted":[140],"samples.":[144],"provides":[148],"competitive":[149],"results":[150],"VTS-based":[153],"method":[154],"while":[155],"cutting":[156],"its":[157],"computational":[158],"overhead":[159],"nearly":[160],"half.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2016-06-24T00:00:00"}