{"id":"https://openalex.org/W3016068446","doi":"https://doi.org/10.1109/icassp40776.2020.9054450","title":"Using Automatic Speech Recognition and Speech Synthesis to Improve the Intelligibility of Cochlear Implant users in Reverberant Listening Environments","display_name":"Using Automatic Speech Recognition and Speech Synthesis to Improve the Intelligibility of Cochlear Implant users in Reverberant Listening Environments","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016068446","doi":"https://doi.org/10.1109/icassp40776.2020.9054450","mag":"3016068446","pmid":"https://pubmed.ncbi.nlm.nih.gov/33078056","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/7568341"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054450","doi":"https://doi.org/10.1109/icassp40776.2020.9054450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054450","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":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7568341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038790801","display_name":"Kevin M. I. Chu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Chu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004578492","display_name":"Leslie M. Collins","orcid":"https://orcid.org/0000-0002-9043-6531","observed_orcids":["https://orcid.org/0000-0002-9043-6531"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leslie Collins","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032974351","display_name":"Boyla O. Mainsah","orcid":"https://orcid.org/0000-0003-2612-0679","observed_orcids":["https://orcid.org/0000-0003-2612-0679"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyla Mainsah","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.9377,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7323545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"2020","issue":null,"first_page":"6929","last_page":"6933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7300000190734863,"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":0.7300000190734863,"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":0.1656000018119812,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.09480000287294388,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cochlear-implants","display_name":"cochlear implants","score":0.8519999980926514},{"id":"https://openalex.org/keywords/reverberant-speech","display_name":"reverberant speech","score":0.9340000152587891},{"id":"https://openalex.org/keywords/speech-intelligibility","display_name":"speech intelligibility","score":0.9620000123977661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9919999837875366},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"speech synthesis","score":0.9139999747276306},{"id":"https://openalex.org/keywords/unknown-environments","display_name":"unknown environments","score":0.640999972820282},{"id":"https://openalex.org/keywords/room-acoustics","display_name":"room acoustics","score":0.7440000176429749},{"id":"https://openalex.org/keywords/vocoded-speech","display_name":"vocoded speech","score":0.8420000076293945},{"id":"https://openalex.org/keywords/speech-recognition-robustness","display_name":"speech recognition robustness","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7928468585014343},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7584709525108337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.734259307384491},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6930347084999084},{"id":"https://openalex.org/C149712133","wikidata":"https://www.wikidata.org/wiki/Q332774","display_name":"Anechoic chamber","level":2,"score":0.6071965098381042},{"id":"https://openalex.org/C2778882171","wikidata":"https://www.wikidata.org/wiki/Q724965","display_name":"Cochlear implant","level":2,"score":0.6065177917480469},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.48514804244041443},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.45570194721221924},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4352286458015442},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.42777976393699646},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4253648817539215},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17857059836387634},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.15639469027519226},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14498671889305115},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.13156557083129883},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.07219889760017395},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054450","doi":"https://doi.org/10.1109/icassp40776.2020.9054450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054450","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":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:33078056","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33078056","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7568341","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7568341","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:7568341","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7568341","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"},"sustainable_development_goals":[{"score":0.4043000042438507,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7513034031","display_name":"Using Machine Learning to Mitigate Reverberation Effects in Cochlear Implants","funder_award_id":"R01DC014290","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W124924985","https://openalex.org/W630361185","https://openalex.org/W1489722190","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1975346954","https://openalex.org/W1975675577","https://openalex.org/W1991298420","https://openalex.org/W2002342963","https://openalex.org/W2031834500","https://openalex.org/W2045043668","https://openalex.org/W2066561607","https://openalex.org/W2106420626","https://openalex.org/W2106554350","https://openalex.org/W2136682440","https://openalex.org/W2148154194","https://openalex.org/W2152051032","https://openalex.org/W2159742781","https://openalex.org/W2161336374","https://openalex.org/W2288817436","https://openalex.org/W2295119550","https://openalex.org/W2471520273","https://openalex.org/W2476684120","https://openalex.org/W2508884455","https://openalex.org/W2525452719","https://openalex.org/W2598638573","https://openalex.org/W2778915404","https://openalex.org/W4233392025","https://openalex.org/W4238685257","https://openalex.org/W6631944105","https://openalex.org/W6727841775"],"related_works":["https://openalex.org/W1489722190","https://openalex.org/W4405709375","https://openalex.org/W2897417605","https://openalex.org/W2800647840","https://openalex.org/W2011264779","https://openalex.org/W4415815239","https://openalex.org/W2295605675","https://openalex.org/W579490996","https://openalex.org/W6908568441","https://openalex.org/W3195626210"],"abstract_inverted_index":{"Cochlear":[0],"implant":[1],"(CI)":[2],"users":[3,145],"experience":[4],"substantial":[5],"difficulties":[6],"in":[7,74,113,130,146],"understanding":[8],"reverberant":[9,25,48,87,148],"speech.":[10,37],"A":[11],"previous":[12],"study":[13,65],"proposed":[14,72],"a":[15,94],"strategy":[16,40,56,126,140],"that":[17,124,137],"leverages":[18],"automatic":[19],"speech":[20,26,28,88,95,101,128],"recognition":[21],"(ASR)":[22],"to":[23,30,59,99],"recognize":[24],"and":[27,43,86,120],"synthesis":[29],"translate":[31],"the":[32,39,46,55,63,67,70,103,107,121,125,138],"recognized":[33],"text":[34,104],"into":[35],"anechoic":[36,85],"However,":[38],"was":[41,82,97],"trained":[42,83,98],"tested":[44],"on":[45,84],"same":[47],"environment,":[49],"so":[50],"it":[51],"is":[52,57],"unknown":[53],"whether":[54],"robust":[58],"unseen":[60,76,132],"environments.":[61,77,149],"Thus,":[62],"current":[64],"investigated":[66],"performance":[68],"of":[69],"previously":[71,131],"algorithm":[73],"multiple":[75],"First,":[78],"an":[79],"ASR":[80,108],"system":[81],"using":[89,117],"different":[90],"room":[91],"types.":[92],"Next,":[93],"synthesizer":[96],"generate":[100],"from":[102],"predicted":[105],"by":[106],"system.":[109],"Experiments":[110],"were":[111],"conducted":[112],"normal":[114],"hearing":[115],"listeners":[116],"vocoded":[118],"speech,":[119],"results":[122,135],"showed":[123],"improved":[127],"intelligibility":[129],"conditions.":[133],"These":[134],"suggest":[136],"ASR-synthesis":[139],"can":[141],"potentially":[142],"benefit":[143],"CI":[144],"everyday":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2020-04-17T00:00:00"}