{"id":"https://openalex.org/W4297841777","doi":"https://doi.org/10.21437/interspeech.2022-615","title":"Correcting Mispronunciations in Speech using Spectrogram Inpainting","display_name":"Correcting Mispronunciations in Speech using Spectrogram Inpainting","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841777","doi":"https://doi.org/10.21437/interspeech.2022-615"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-615","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-615","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","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/A5066408476","display_name":"Talia Ben Simon","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Talia Ben Simon","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000406733","display_name":"Felix Kreuk","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Felix Kreuk","raw_affiliation_strings":["Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084266704","display_name":"Faten Awwad","orcid":null},"institutions":[{"id":"https://openalex.org/I2801301638","display_name":"Rambam Health Care Campus","ror":"https://ror.org/01fm87m50","country_code":"IL","type":"healthcare","lineage":["https://openalex.org/I2801301638"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Faten Awwad","raw_affiliation_strings":["Department of Otolaryngology Head and Neck Surgery, Rambam Health Care Campus, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otolaryngology Head and Neck Surgery, Rambam Health Care Campus, Israel","institution_ids":["https://openalex.org/I2801301638"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050519102","display_name":"Jacob T. Cohen","orcid":"https://orcid.org/0000-0002-1160-0234"},"institutions":[{"id":"https://openalex.org/I2801301638","display_name":"Rambam Health Care Campus","ror":"https://ror.org/01fm87m50","country_code":"IL","type":"healthcare","lineage":["https://openalex.org/I2801301638"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jacob T. Cohen","raw_affiliation_strings":["Department of Otolaryngology Head and Neck Surgery, Rambam Health Care Campus, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otolaryngology Head and Neck Surgery, Rambam Health Care Campus, Israel","institution_ids":["https://openalex.org/I2801301638"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008847407","display_name":"Joseph Keshet","orcid":"https://orcid.org/0000-0003-2332-5783"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Joseph Keshet","raw_affiliation_strings":["Facullty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facullty of Electrical and Computer Engineering, Technion-Israel Institute of Technology, Israel","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008847407"],"corresponding_institution_ids":["https://openalex.org/I174306211"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1208","last_page":"1212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9977999925613403,"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/spectrogram","display_name":"Spectrogram","score":0.9255948662757874},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.6442469358444214},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6176074743270874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5736947059631348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33712318539619446},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.113501638174057}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9255948662757874},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.6442469358444214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6176074743270874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5736947059631348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33712318539619446},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.113501638174057}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-615","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-615","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W269898920","https://openalex.org/W395277161","https://openalex.org/W1707296401","https://openalex.org/W1901129140","https://openalex.org/W1975456328","https://openalex.org/W2008066109","https://openalex.org/W2022817592","https://openalex.org/W2032764520","https://openalex.org/W2116037506","https://openalex.org/W2624866404","https://openalex.org/W2747874407","https://openalex.org/W2798365772","https://openalex.org/W2833335833","https://openalex.org/W2896599145","https://openalex.org/W2899000566","https://openalex.org/W2901544281","https://openalex.org/W2963276790","https://openalex.org/W2963300588","https://openalex.org/W2972970915","https://openalex.org/W2973142754","https://openalex.org/W2981283774","https://openalex.org/W2981905048","https://openalex.org/W2985518820","https://openalex.org/W3092028330","https://openalex.org/W3105183525","https://openalex.org/W3163457913","https://openalex.org/W4289765851"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2380775572","https://openalex.org/W2213520135","https://openalex.org/W2244018504","https://openalex.org/W4242046654","https://openalex.org/W3174923100","https://openalex.org/W2135359786","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Learning":[0],"a":[1,29,41,72,95,100,106,113,169,177,180],"new":[2],"language":[3,30],"involves":[4],"constantly":[5],"comparing":[6],"speech":[7,16,33,74,96,123,167],"productions":[8,11],"with":[9,81,87,105,156,176],"reference":[10],"from":[12],"the":[13,36,57,62,68,78,82,126,132,137,173],"environment.Early":[14],"in":[15],"acquisition,":[17],"children":[18,155],"make":[19],"articulatory":[20],"adjustments":[21],"to":[22,34,43,55,70,94,111,130],"match":[23,35],"their":[24,32],"caregivers'":[25],"speech.Grownup":[26],"learners":[27],"of":[28,120,139,145,149,172,179],"tweak":[31],"tutor":[37],"reference.This":[38],"paper":[39],"proposes":[40],"method":[42],"synthetically":[44],"generate":[45,56],"correct":[46],"pronunciation":[47,157],"feedback":[48],"given":[49],"incorrect":[50],"production.Furthermore,":[51],"our":[52,140,165],"aim":[53],"is":[54,75,118,128],"corrected":[58],"production":[59,178],"while":[60],"maintaining":[61],"speaker's":[63],"original":[64,133],"voice.The":[65],"system":[66,104,141],"prompts":[67],"user":[69],"pronounce":[71],"phrase.The":[73],"recorded,":[76],"and":[77,109,125],"samples":[79],"associated":[80],"inaccurate":[83,174],"phoneme":[84,143,175],"are":[85],"masked":[86],"zeros.This":[88],"waveform":[89],"serves":[90],"as":[91,99,151,153],"an":[92],"input":[93],"generator,":[97],"implemented":[98],"deep":[101],"learning":[102],"inpainting":[103],"U-net":[107],"architecture,":[108],"trained":[110,129],"output":[112],"reconstructed":[114],"speech.The":[115],"training":[116],"set":[117],"composed":[119],"unimpaired":[121],"proper":[122,134],"examples,":[124],"generator":[127],"reconstruct":[131],"speech.We":[135],"evaluated":[136],"performance":[138],"on":[142,154],"replacement":[144,171],"minimal":[146],"pair":[147],"words":[148],"English":[150],"well":[152],"disorders.Results":[158],"suggest":[159],"that":[160],"human":[161],"listeners":[162],"slightly":[163],"prefer":[164],"generated":[166],"over":[168],"smoothed":[170],"different":[181],"speaker.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}