{"id":"https://openalex.org/W4296068592","doi":"https://doi.org/10.21437/interspeech.2022-438","title":"Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech","display_name":"Improving Hypernasality Estimation with Automatic Speech Recognition in Cleft Palate Speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068592","doi":"https://doi.org/10.21437/interspeech.2022-438"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-438","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":"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":"https://openalex.org/A5028035527","display_name":"Kaitao Song","orcid":"https://orcid.org/0000-0002-4046-8594"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kaitao Song","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110657626","display_name":"Teng Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210097066","display_name":"Shanghai Ninth People's Hospital","ror":"https://ror.org/010826a91","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097066"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Wan","raw_affiliation_strings":["Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,"],"affiliations":[{"raw_affiliation_string":"Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","institution_ids":["https://openalex.org/I4210097066"]},{"raw_affiliation_string":"Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109524282","display_name":"Bixia Wang","orcid":"https://orcid.org/0000-0002-9535-1182"},"institutions":[{"id":"https://openalex.org/I4210097066","display_name":"Shanghai Ninth People's Hospital","ror":"https://ror.org/010826a91","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097066"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bixia Wang","raw_affiliation_strings":["Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,"],"affiliations":[{"raw_affiliation_string":"Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","institution_ids":["https://openalex.org/I4210097066"]},{"raw_affiliation_string":"Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070156365","display_name":"Huiqiang Jiang","orcid":"https://orcid.org/0000-0002-1327-4882"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiqiang Jiang","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062706827","display_name":"Luna Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luna Qiu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065385916","display_name":"Jiahang Xu","orcid":"https://orcid.org/0000-0001-9186-619X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiahang Xu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079447763","display_name":"Liping Jiang","orcid":"https://orcid.org/0000-0002-1785-7225"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210097066","display_name":"Shanghai Ninth People's Hospital","ror":"https://ror.org/010826a91","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097066"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Jiang","raw_affiliation_strings":["Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,"],"affiliations":[{"raw_affiliation_string":"Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","institution_ids":["https://openalex.org/I4210097066"]},{"raw_affiliation_string":"Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049807131","display_name":"Qun Lou","orcid":"https://orcid.org/0000-0003-1668-119X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210097066","display_name":"Shanghai Ninth People's Hospital","ror":"https://ror.org/010826a91","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097066"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Lou","raw_affiliation_strings":["Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,"],"affiliations":[{"raw_affiliation_string":"Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","institution_ids":["https://openalex.org/I4210097066"]},{"raw_affiliation_string":"Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101421201","display_name":"Yuqing Yang","orcid":"https://orcid.org/0000-0003-3518-5212"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuqing Yang","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440920","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0003-3103-8442"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100348166","display_name":"Xudong Wang","orcid":"https://orcid.org/0000-0003-3697-4651"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210097066","display_name":"Shanghai Ninth People's Hospital","ror":"https://ror.org/010826a91","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210097066"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Wang","raw_affiliation_strings":["Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,","Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University School of Medicine {kaitaosong, hjiang, lunaqiu, jiahangxu, Yuqing.Yang,","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Oral and Craniomaxillofacial Surgery, Shanghai Ninth People's Hospital,","institution_ids":["https://openalex.org/I4210097066"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032760128","display_name":"Lili Qiu","orcid":"https://orcid.org/0000-0002-1590-9749"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lili Qiu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5028035527"],"corresponding_institution_ids":["https://openalex.org/I4210164937"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.67533937,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4820","last_page":"4824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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/T11374","display_name":"Cleft Lip and Palate Research","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9839000105857849,"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/speech-recognition","display_name":"Speech recognition","score":0.7556043863296509},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7129251956939697},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5052221417427063},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42199116945266724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3669086694717407},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.334443598985672},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10564550757408142}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7556043863296509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7129251956939697},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5052221417427063},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42199116945266724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3669086694717407},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.334443598985672},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10564550757408142},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-438","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2028904426","https://openalex.org/W2029730402","https://openalex.org/W2048251069","https://openalex.org/W2079599531","https://openalex.org/W2115560088","https://openalex.org/W2130942839","https://openalex.org/W2406232468","https://openalex.org/W2528914055","https://openalex.org/W2588491049","https://openalex.org/W2747395251","https://openalex.org/W2896457183","https://openalex.org/W2938850633","https://openalex.org/W2945176360","https://openalex.org/W2945331428","https://openalex.org/W2963242190","https://openalex.org/W2973049979","https://openalex.org/W2973143332","https://openalex.org/W2990683251","https://openalex.org/W3015897612","https://openalex.org/W3015995734","https://openalex.org/W3092424727","https://openalex.org/W3129068537","https://openalex.org/W3160545708","https://openalex.org/W4295224294","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"Hypernasality":[0],"is":[1,23],"an":[2,41,95,99],"abnormal":[3],"resonance":[4],"in":[5,10,25,98,152,165],"human":[6],"speech":[7,38,85,101,150],"production,":[8],"especially":[9],"patients":[11],"with":[12,139,189],"craniofacial":[13],"anomalies":[14],"such":[15,123],"as":[16,29],"cleft":[17,26,65,116,141,178],"palate.In":[18],"clinical":[19],"application,":[20],"hypernasality":[21,43,56,90,120,128],"estimation":[22,57,129],"crucial":[24],"palate":[27,66,117,142,179],"diagnosis,":[28],"its":[30],"results":[31,175],"determine":[32],"the":[33,115,132,144,153,162],"subsequent":[34],"surgery":[35],"and":[36,109],"additional":[37],"therapy.Therefore,":[39],"designing":[40],"automatic":[42,84,100],"assessment":[44],"method":[45,184],"will":[46],"facilitate":[47],"speech-language":[48],"pathologists":[49],"to":[50,88,170],"make":[51],"precise":[52],"diagnoses.Existing":[53],"methods":[54],"for":[55,119,127],"only":[58],"conduct":[59],"acoustic":[60,173],"analysis":[61],"based":[62],"on":[63,114,176],"low-resource":[64,140],"dataset,":[67,108,143],"by":[68,105],"using":[69,106],"statistical":[70],"or":[71],"neural":[72],"network-based":[73],"features.In":[74],"this":[75],"paper,":[76],"we":[77,92],"propose":[78],"a":[79],"novel":[80],"approach":[81],"that":[82,182],"uses":[83],"recognition":[86,102],"model":[87,126,159,169],"improve":[89],"estimation.Specifically,":[91],"first":[93],"pre-train":[94],"encoder-decoder":[96],"framework":[97],"(ASR)":[103],"objective":[104],"speech-to-text":[107],"then":[110],"fine-tune":[111],"ASR":[112,135,145,166],"encoder":[113],"dataset":[118,167],"estimation.Benefiting":[121],"from":[122],"design,":[124],"our":[125,183],"can":[130],"enjoy":[131],"advantages":[133],"of":[134],"model:":[136],"1)":[137],"compared":[138,188],"task":[146],"usually":[147],"includes":[148],"large-scale":[149],"data":[151],"general":[154],"domain,":[155],"which":[156],"enables":[157],"better":[158,172],"generalization;":[160],"2)":[161],"text":[163],"annotations":[164],"guide":[168],"extract":[171],"features.Experimental":[174],"two":[177],"datasets":[180],"demonstrate":[181],"achieves":[185],"superior":[186],"performance":[187],"previous":[190],"approaches.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
