{"id":"https://openalex.org/W4405490541","doi":"https://doi.org/10.1109/embc53108.2024.10782916","title":"Research on Tone Enhancement of Mandarin Pitch Controllable Electrolaryngeal Speech Based on Deep Learning","display_name":"Research on Tone Enhancement of Mandarin Pitch Controllable Electrolaryngeal Speech Based on Deep Learning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4405490541","doi":"https://doi.org/10.1109/embc53108.2024.10782916","pmid":"https://pubmed.ncbi.nlm.nih.gov/40039465"},"language":"en","primary_location":{"id":"doi:10.1109/embc53108.2024.10782916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"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/A5100620310","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0003-2094-4255"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100336197","display_name":"Li Wang","orcid":"https://orcid.org/0000-0003-2165-0080"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035311905","display_name":"Fengji Li","orcid":"https://orcid.org/0000-0002-6575-6920"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengji Li","raw_affiliation_strings":["Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010005668","display_name":"Shaochuan Zhang","orcid":"https://orcid.org/0000-0002-4853-4525"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaochuan Zhang","raw_affiliation_strings":["Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115595739","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0001-9529-6550"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaohong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I1294606314","display_name":"Beijing Tongren Hospital","ror":"https://ror.org/013e4n276","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294606314"]},{"id":"https://openalex.org/I183519381","display_name":"Capital Medical University","ror":"https://ror.org/013xs5b60","country_code":"CN","type":"education","lineage":["https://openalex.org/I183519381"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohong Chen","raw_affiliation_strings":["Capital Medical University,Beijing Tongren Hospital,Department of Otolaryngology, Head and Neck Surgery,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital Medical University,Beijing Tongren Hospital,Department of Otolaryngology, Head and Neck Surgery,Beijing,China","institution_ids":["https://openalex.org/I1294606314","https://openalex.org/I183519381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101909579","display_name":"Haijun Niu","orcid":"https://orcid.org/0000-0001-8891-6846"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haijun Niu","raw_affiliation_strings":["Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University,Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering,Beijing,China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"2024","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9926000237464905,"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":0.9926000237464905,"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":0.9833999872207642,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9751999974250793,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9324226379394531},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.7738004326820374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7144496440887451},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6067405939102173},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49164730310440063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34232309460639954},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07955792546272278},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0746602714061737}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9324226379394531},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.7738004326820374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7144496440887451},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067405939102173},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49164730310440063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34232309460639954},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07955792546272278},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0746602714061737},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013061","descriptor_name":"Speech Acoustics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013061","descriptor_name":"Speech Acoustics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013061","descriptor_name":"Speech Acoustics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013071","descriptor_name":"Speech, Alaryngeal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013071","descriptor_name":"Speech, Alaryngeal","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013071","descriptor_name":"Speech, Alaryngeal","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc53108.2024.10782916","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782916","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:40039465","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40039465","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,"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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321496","display_name":"Capital Medical University","ror":"https://ror.org/013xs5b60"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1601338078","https://openalex.org/W2020100683","https://openalex.org/W2022125261","https://openalex.org/W2677089859","https://openalex.org/W2789445670","https://openalex.org/W2902070858","https://openalex.org/W2950542544","https://openalex.org/W3096359062","https://openalex.org/W3098557217","https://openalex.org/W3114898335","https://openalex.org/W4306155393","https://openalex.org/W4406859288","https://openalex.org/W6790749447"],"related_works":["https://openalex.org/W2393887907","https://openalex.org/W2347443630","https://openalex.org/W2481138693","https://openalex.org/W2388826840","https://openalex.org/W2379831327","https://openalex.org/W2386691339","https://openalex.org/W156219719","https://openalex.org/W2365805939","https://openalex.org/W2287147624","https://openalex.org/W2980894105"],"abstract_inverted_index":{"The":[0,28,129,153,222],"deep":[1],"learning-based":[2],"electrolaryngeal":[3],"(EL)":[4],"voice":[5],"conversion":[6,118],"methods":[7],"have":[8,218],"achieved":[9],"good":[10],"results":[11,119,130,223],"in":[12,18,82,123,143,235,250],"non-tonal":[13],"languages.":[14],"However,":[15],"the":[16,33,46,72,76,89,104,112,117,133,140,174,179,186,197,212,215,226],"effectiveness":[17],"tonal":[19,56,251],"languages,":[20,252],"such":[21,165],"as":[22,166],"Mandarin":[23,73,124,236],"Chinese":[24],"(Mandarin),":[25],"remains":[26],"suboptimal.":[27],"reason":[29],"may":[30],"be":[31,230],"that":[32,132,170,211,225],"EL":[34,49,188,238,247],"speech":[35,50,57,90,248],"lacks":[36],"any":[37],"tone":[38,146,148,151,233],"information.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"further":[44],"improved":[45,202],"quality":[47],"of":[48,99,106,120,145,214],"by":[51,63],"initially":[52],"generating":[53],"a":[54,59,65,97,243],"basic":[55],"using":[58],"pitch-controlled":[60,237],"electrolarynx,":[61],"followed":[62],"employing":[64],"generative":[66],"model":[67,81],"to":[68,139,173,194,205,232],"refine":[69],"and":[70,127,150,168,258],"enhance":[71],"tones.":[74,176],"Utilizing":[75],"cycle-consistent":[77],"adversarial":[78],"networks":[79],"(CycleGAN)":[80],"conjunction":[83],"with":[84],"continuous":[85],"wavelet":[86],"transformation":[87],"techniques,":[88],"fundamental":[91],"frequency":[92,101],"(F0)":[93],"is":[94],"decomposed":[95],"into":[96,111],"hierarchy":[98],"multiple":[100],"scales,":[102],"enhancing":[103],"granularity":[105],"feature":[107],"extraction.":[108],"Then":[109],"fed":[110],"CycleGAN":[113],"for":[114,185,246,255],"training.":[115],"Finally,":[116],"four":[121,187],"tones":[122,135,142,155,189,217],"are":[125,136,171],"compared":[126],"evaluated.":[128],"show":[131,210],"converted":[134,154,216],"significantly":[137,201],"closer":[138],"normal":[141,175],"terms":[144],"contour,":[147],"range,":[149],"value.":[152],"not":[156],"only":[157],"exhibit":[158],"smoother,":[159],"but":[160],"also":[161],"display":[162],"some":[163],"details":[164],"\"offset-section":[167],"onset-section\"":[169],"similar":[172],"After":[177],"conversion,":[178],"F0":[180,198],"root":[181],"mean":[182],"square":[183],"error":[184],"markedly":[190],"decreased":[191],"from":[192,203],"1.106":[193],"0.277,":[195],"while":[196],"correlation":[199],"coefficient":[200],"0.393":[204],"0.781.":[206],"Two":[207],"evaluation":[208],"indexes":[209],"accuracy":[213],"been":[219],"greatly":[220],"improved.":[221],"demonstrate":[224],"proposed":[227],"method":[228],"can":[229],"applied":[231],"enhancement":[234,249],"speech.":[239],"This":[240],"study":[241],"opens":[242],"new":[244],"way":[245],"offering":[253],"potential":[254],"future":[256],"research":[257],"application.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}
