{"id":"https://openalex.org/W4385823183","doi":"https://doi.org/10.21437/interspeech.2023-113","title":"mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra","display_name":"mdctGAN: Taming transformer-based GAN for speech super-resolution with Modified DCT spectra","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823183","doi":"https://doi.org/10.21437/interspeech.2023-113"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://bura.brunel.ac.uk/bitstream/2438/29080/1/FullText.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058042026","display_name":"Chenhao Shuai","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN","SG"],"is_corresponding":true,"raw_author_name":"Chenhao Shuai","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications, China","Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104156089","display_name":"Chaohua Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]},{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaohua Shi","raw_affiliation_strings":["Xidian University, China","Chongqing University of Posts and Telecommunications, China"],"affiliations":[{"raw_affiliation_string":"Xidian University, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032405819","display_name":"Lu Gan","orcid":"https://orcid.org/0000-0003-2138-9564"},"institutions":[{"id":"https://openalex.org/I59433898","display_name":"Brunel University of London","ror":"https://ror.org/00dn4t376","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I59433898"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lu Gan","raw_affiliation_strings":["Brunel University London, UK"],"affiliations":[{"raw_affiliation_string":"Brunel University London, UK","institution_ids":["https://openalex.org/I59433898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102001094","display_name":"Hongqing Liu","orcid":"https://orcid.org/0000-0002-2069-0390"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongqing Liu","raw_affiliation_strings":["Chongqing University of Posts and Telecommunications, China","Intelligent Speech and Audio Lab, CQUPT"],"affiliations":[{"raw_affiliation_string":"Chongqing University of Posts and Telecommunications, China","institution_ids":["https://openalex.org/I10535382"]},{"raw_affiliation_string":"Intelligent Speech and Audio Lab, CQUPT","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5058042026"],"corresponding_institution_ids":["https://openalex.org/I10535382","https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.0604,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79263503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5112","last_page":"5116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9976000189781189,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.733934223651886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7279146313667297},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6796454191207886},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6472982168197632},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5661651492118835},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48688140511512756},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4601254463195801},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4326328635215759},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33853358030319214},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.329730361700058},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.32019490003585815},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11793974041938782},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09523755311965942},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07515931129455566},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07514163851737976}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.733934223651886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279146313667297},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6796454191207886},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6472982168197632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5661651492118835},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48688140511512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4601254463195801},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4326328635215759},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33853358030319214},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.329730361700058},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.32019490003585815},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11793974041938782},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09523755311965942},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07515931129455566},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07514163851737976},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-113","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:bura.brunel.ac.uk:2438/29080","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/29080","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/29080/1/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of INTERSPEECH 2023","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:bura.brunel.ac.uk:2438/29080","is_oa":true,"landing_page_url":"https://bura.brunel.ac.uk/handle/2438/29080","pdf_url":"http://bura.brunel.ac.uk/bitstream/2438/29080/1/FullText.pdf","source":{"id":"https://openalex.org/S4306401473","display_name":"Brunel University Research Archive (BURA) (Brunel University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59433898","host_organization_name":"Brunel University of London","host_organization_lineage":["https://openalex.org/I59433898"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of INTERSPEECH 2023","raw_type":"Conference Paper"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823183.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1970308149","https://openalex.org/W2519091744","https://openalex.org/W2763421725","https://openalex.org/W2940120659","https://openalex.org/W2963800363","https://openalex.org/W2963952344","https://openalex.org/W2970006822","https://openalex.org/W3092028330","https://openalex.org/W3096408984","https://openalex.org/W3125868443","https://openalex.org/W3197334236","https://openalex.org/W3197990672","https://openalex.org/W3198020407","https://openalex.org/W3198680319","https://openalex.org/W3213952100","https://openalex.org/W4283215837","https://openalex.org/W4297778191","https://openalex.org/W4320013936","https://openalex.org/W4372262687","https://openalex.org/W4375869358","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W4388016426","https://openalex.org/W4386746628","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Speech":[0],"super-resolution":[1],"(SSR)":[2],"aims":[3],"to":[4],"recover":[5],"a":[6,46,69,87],"high":[7,88,107],"resolution":[8,15,123],"(HR)":[9],"speech":[10,90],"from":[11,124],"its":[12],"corresponding":[13],"low":[14],"(LR)":[16],"counterpart.Recent":[17],"SSR":[18,48],"methods":[19],"focus":[20],"more":[21],"on":[22,51,119],"the":[23,26,30,37,60,95,114],"reconstruction":[24],"of":[25,32],"magnitude":[27],"spectrogram,":[28],"ignoring":[29],"importance":[31],"phase":[33],"reconstruction,":[34],"thereby":[35],"limiting":[36],"recovery":[38],"quality.To":[39],"address":[40],"this":[41],"issue,":[42],"we":[43],"propose":[44],"mdctGAN,":[45],"novel":[47],"framework":[49],"based":[50],"modified":[52],"discrete":[53],"cosine":[54],"transform":[55],"(MDCT).By":[56],"adversarial":[57],"learning":[58,78],"in":[59,68],"MDCT":[61],"domain,":[62],"our":[63,100],"method":[64],"reconstructs":[65],"HR":[66],"speeches":[67],"phase-aware":[70],"manner":[71],"without":[72],"vocoders":[73],"or":[74],"additional":[75],"post-processing.Furthermore,":[76],"by":[77],"frequency":[79],"consistent":[80],"features":[81],"with":[82,106],"self-attentive":[83],"mechanism,":[84],"mdctGAN":[85],"guarantees":[86],"quality":[89,105],"reconstruction.For":[91],"VCTK":[92],"corpus":[93],"dataset,":[94],"experiment":[96],"results":[97],"show":[98],"that":[99],"model":[101],"produces":[102],"natural":[103],"auditory":[104],"MOS":[108],"and":[109],"PESQ":[110],"scores.It":[111],"also":[112],"achieves":[113],"state-of-theart":[115],"log-spectral-distance":[116],"(LSD)":[117],"performance":[118],"48":[120],"kHz":[121],"target":[122],"various":[125],"input":[126],"rates.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}