{"id":"https://openalex.org/W2767064007","doi":"https://doi.org/10.1007/s10772-017-9461-x","title":"Deep neural network training for whispered speech recognition using small databases and generative model sampling","display_name":"Deep neural network training for whispered speech recognition using small databases and generative model sampling","publication_year":2017,"publication_date":"2017-10-26","ids":{"openalex":"https://openalex.org/W2767064007","doi":"https://doi.org/10.1007/s10772-017-9461-x","mag":"2767064007"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-017-9461-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-017-9461-x","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10772-017-9461-x.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10772-017-9461-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040866561","display_name":"Shabnam Ghaffarzadegan","orcid":null},"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":true,"raw_author_name":"Shabnam Ghaffarzadegan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, 75083-0688, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, 75083-0688, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009895165","display_name":"Hynek Bo\u0159il","orcid":null},"institutions":[{"id":"https://openalex.org/I1745920","display_name":"University of Wisconsin\u2013Platteville","ror":"https://ror.org/02xpkhc07","country_code":"US","type":"education","lineage":["https://openalex.org/I1745920"]},{"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 Bo\u0159il","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, 75083-0688, USA","Electrical Engineering Department, UW-Platteville, Platteville, WI, 53818-3099, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, 75083-0688, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Electrical Engineering Department, UW-Platteville, Platteville, WI, 53818-3099, USA","institution_ids":["https://openalex.org/I1745920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"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, TX, 75083-0688, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, 75083-0688, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040866561"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2780},"apc_paid":{"value":2190,"currency":"EUR","value_usd":2780},"fwci":1.2472,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85589709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"20","issue":"4","first_page":"1063","last_page":"1075"},"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":0.9995999932289124,"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":0.9976000189781189,"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":0.855898916721344},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7881221771240234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6809142231941223},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6027461290359497},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5936194062232971},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49834752082824707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48417240381240845},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.47666245698928833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46204373240470886},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.43598172068595886},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43013402819633484},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3147178292274475},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.22525978088378906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855898916721344},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7881221771240234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6809142231941223},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6027461290359497},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5936194062232971},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49834752082824707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48417240381240845},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.47666245698928833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46204373240470886},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.43598172068595886},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43013402819633484},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3147178292274475},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.22525978088378906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-017-9461-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-017-9461-x","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10772-017-9461-x.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10772-017-9461-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-017-9461-x","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10772-017-9461-x.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G8087301405","display_name":null,"funder_award_id":"FA8750-15-1-0205","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"},{"id":"https://openalex.org/G8689538958","display_name":null,"funder_award_id":"FA8750-12-1-0188","funder_id":"https://openalex.org/F4320338294","funder_display_name":"Air Force Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320327708","display_name":"University of Texas at Dallas","ror":"https://ror.org/049emcs32"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2767064007.pdf","grobid_xml":"https://content.openalex.org/works/W2767064007.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W41355022","https://openalex.org/W109189503","https://openalex.org/W128467325","https://openalex.org/W621546036","https://openalex.org/W1502652411","https://openalex.org/W1524333225","https://openalex.org/W1980800561","https://openalex.org/W2000595281","https://openalex.org/W2002342963","https://openalex.org/W2010354425","https://openalex.org/W2026369565","https://openalex.org/W2043756700","https://openalex.org/W2045956438","https://openalex.org/W2050693797","https://openalex.org/W2055589033","https://openalex.org/W2062164080","https://openalex.org/W2076092328","https://openalex.org/W2091432990","https://openalex.org/W2125838338","https://openalex.org/W2129741985","https://openalex.org/W2137075158","https://openalex.org/W2137919539","https://openalex.org/W2142197202","https://openalex.org/W2147768505","https://openalex.org/W2147944429","https://openalex.org/W2148154194","https://openalex.org/W2152051032","https://openalex.org/W2153939756","https://openalex.org/W2160815625","https://openalex.org/W2162366669","https://openalex.org/W2163614729","https://openalex.org/W2163738067","https://openalex.org/W2184045248","https://openalex.org/W2294831733","https://openalex.org/W2394932179","https://openalex.org/W2405895519","https://openalex.org/W2437658533","https://openalex.org/W2478027467","https://openalex.org/W6604418364","https://openalex.org/W6631362777","https://openalex.org/W6638674303","https://openalex.org/W6680388406"],"related_works":["https://openalex.org/W2735380212","https://openalex.org/W2018887914","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2785476196","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534"],"abstract_inverted_index":{"State-of-the-art":[0],"speech":[1,17,185,206,240],"recognition":[2],"solutions":[3],"currently":[4],"employ":[5],"hidden":[6],"Markov":[7],"models":[8],"(HMMs)":[9],"to":[10,24,55,60,105,137,151,165,176,198],"capture":[11,138],"the":[12,26,56,124,143,159,167,172,179,188,194,200,223,247,251],"time":[13],"variability":[14],"in":[15,47,75,171,250],"a":[16,77,82,103,117,130,139,153,183,205,237],"signal":[18],"and":[19,41,218,257,266],"deep":[20],"neural":[21],"networks":[22],"(DNNs)":[23],"model":[25,44,61,133,203],"HMM":[27,40],"state":[28],"distributions.":[29,145],"It":[30,228],"has":[31],"been":[32],"shown":[33,230],"that":[34,112,231],"DNN\u2013HMM":[35,201,238],"hybrid":[36],"systems":[37],"outperform":[38],"traditional":[39],"Gaussian":[42],"mixture":[43],"(GMM)":[45],"hybrids":[46],"many":[48,91],"applications.":[49],"This":[50,85],"improvement":[51],"is":[52,71,135,149,162,211,229],"mainly":[53],"attributed":[54],"ability":[57],"of":[58,96,110,115,120,142,156,182,204,216,236],"DNNs":[59,88],"more":[62],"complex":[63],"data":[64,69,122,144,197,220],"structures.":[65],"However,":[66],"having":[67],"sufficient":[68],"samples":[70],"one":[72],"key":[73],"point":[74],"training":[76,196,252],"high":[78],"accuracy":[79],"DNN":[80],"as":[81],"discriminative":[83],"model.":[84],"barrier":[86],"makes":[87],"unsuitable":[89],"for":[90,263],"applications":[92],"with":[93,193,254],"limited":[94],"amounts":[95],"data.":[97],"In":[98,127],"this":[99,128],"study,":[100],"we":[101],"introduce":[102],"method":[104,210],"produce":[106],"an":[107],"excessive":[108],"amount":[109,119,155],"pseudo-samples":[111,157,249],"requires":[113],"availability":[114],"only":[116],"small":[118],"transcribed":[121],"from":[123,158,222],"target":[125],"domain.":[126],"method,":[129],"universal":[131],"background":[132],"(UBM)":[134],"trained":[136],"parametric":[140],"estimate":[141],"Next,":[146],"random":[147],"sampling":[148],"used":[150],"generate":[152],"large":[154],"UBM.":[160],"Frame-Shuffling":[161],"then":[163],"applied":[164],"smooth":[166],"temporal":[168,180],"cepstral":[169],"trajectories":[170],"generated":[173,248],"pseudo-sample":[174,189],"sequences":[175,190],"better":[177],"resemble":[178],"characteristics":[181],"natural":[184],"signal.":[186],"Finally,":[187],"are":[191,242],"combined":[192],"original":[195],"train":[199],"acoustic":[202],"recognizer.":[207],"The":[208],"proposed":[209],"evaluated":[212],"on":[213],"small-sized":[214],"sets":[215],"neutral":[217],"whisper":[219],"drawn":[221],"UT-Vocal":[224],"Effort":[225],"II":[226],"corpus.":[227],"phoneme":[232],"error":[233],"rates":[234],"(PERs)":[235],"based":[239],"recognizer":[241],"considerably":[243],"reduced":[244],"when":[245],"incorporating":[246],"process,":[253],"+":[255,258],"79.0":[256],"45.6%":[259],"relative":[260],"PER":[261],"improvements":[262],"neutral\u2013neutral":[264],"training/test":[265,268],"whisper\u2013whisper":[267],"scenarios,":[269],"respectively.":[270]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}