{"id":"https://openalex.org/W192531825","doi":"https://doi.org/10.21437/eurospeech.1999-519","title":"Voice conversion between UK and US accented English","display_name":"Voice conversion between UK and US accented English","publication_year":1999,"publication_date":"1999-09-05","ids":{"openalex":"https://openalex.org/W192531825","doi":"https://doi.org/10.21437/eurospeech.1999-519","mag":"192531825"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1999-519","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","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":null,"display_name":"Ching-Hsiang Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ching-Hsiang Ho","raw_affiliation_strings":["[Tampere Univ. of Tech.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Tampere Univ. of Tech.]","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Saeed Vaseghi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saeed Vaseghi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Aimin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aimin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3732,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.57516183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2079","last_page":"2082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.769190788269043},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.747173011302948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228220701217651},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6871461272239685},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6441059708595276},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.633331835269928},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5726252198219299},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5514859557151794},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5375139117240906},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.5049896836280823},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.47704142332077026},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4702303111553192},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45721885561943054},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.45331478118896484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40546393394470215},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3596538007259369},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32667702436447144},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.21947047114372253},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1844475269317627},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10942849516868591}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.769190788269043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.747173011302948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228220701217651},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6871461272239685},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6441059708595276},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.633331835269928},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5726252198219299},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5514859557151794},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5375139117240906},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5049896836280823},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.47704142332077026},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4702303111553192},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45721885561943054},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.45331478118896484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40546393394470215},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3596538007259369},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32667702436447144},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.21947047114372253},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1844475269317627},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10942849516868591},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.1999-519","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1999-519","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th European Conference on Speech Communication and Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2002096058","https://openalex.org/W2033245860","https://openalex.org/W2038054257","https://openalex.org/W2045036776","https://openalex.org/W2101349570","https://openalex.org/W2103496339","https://openalex.org/W2109349638","https://openalex.org/W2163348148","https://openalex.org/W2164720542"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2953493266","https://openalex.org/W4252682934","https://openalex.org/W2851491717","https://openalex.org/W2135485548","https://openalex.org/W2072884270","https://openalex.org/W2356426224","https://openalex.org/W2373767407"],"abstract_inverted_index":{"The":[0,47,101,127,153],"performance":[1,34],"of":[2,12,35,103,129,168],"voice":[3,37],"dialling":[4,38],"systems":[5],"often":[6],"degrades":[7],"rapidly":[8],"as":[9],"the":[10,13,31,89,104,113,130,139],"intensity":[11],"background":[14],"noise":[15,61,64,70,115,141,163],"increases.":[16],"In":[17],"this":[18],"paper,":[19],"we":[20],"describe":[21],"a":[22,36,67,80,92],"neural":[23],"network":[24,86],"based":[25,97],"speech":[26,32,48,72,98],"enhancement":[27],"technique":[28],"for":[29,158],"improving":[30],"recognition":[33,90,99],"system":[39],"in":[40,52,66,76,112,138],"very":[41],"noisy":[42],"real":[43],"world":[44],"type":[45],"conditions.":[46],"samples":[49,73],"were":[50,74],"recorded":[51,65],"laboratory":[53],"conditions":[54],"and":[55,110,122,136,149,161],"afterwards":[56],"corrupted":[57,71],"by":[58,79],"adding":[59],"car":[60,114,160],"or":[62],"babble":[63,140,162],"cafe.":[68],"These":[69],"enhanced":[75],"cepstral":[77],"domain":[78],"context":[81],"dependent":[82],"multilayer":[83],"perceptron":[84],"(MLP)":[85],"before":[87],"performing":[88],"using":[91],"hidden":[93],"Markov":[94],"model":[95],"(HMM)":[96],"system.":[100],"accuracy":[102,128,154],"test":[105,131],"set":[106,132],"increased":[107,133],"58%,":[108],"55%":[109],"46%":[111],"environments":[116,142,164],"having":[117,143,166],"-5":[118],"dB,":[119,146,151],"0":[120],"dB":[121,124,148],"5":[123,145],"SNRs,":[125],"respectively.":[126,152],"44%,":[134],"48%":[135],"39%":[137],"SNR":[144,167],"10":[147],"15":[150],"remained":[155],"approximately":[156],"same":[157],"both":[159],"when":[165],"20":[169],"dB.":[170]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}