{"id":"https://openalex.org/W4404031501","doi":"https://doi.org/10.1109/icccnt61001.2024.10724686","title":"Generative Adversarial Network-Based Voice Synthesis from Spectrograms for Low-Resource Speech Recognition in Mismatched Conditions","display_name":"Generative Adversarial Network-Based Voice Synthesis from Spectrograms for Low-Resource Speech Recognition in Mismatched Conditions","publication_year":2024,"publication_date":"2024-06-24","ids":{"openalex":"https://openalex.org/W4404031501","doi":"https://doi.org/10.1109/icccnt61001.2024.10724686"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt61001.2024.10724686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt61001.2024.10724686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5076299882","display_name":"Puneet Bawa","orcid":"https://orcid.org/0000-0001-5508-537X"},"institutions":[{"id":"https://openalex.org/I74319210","display_name":"Chitkara University","ror":"https://ror.org/057d6z539","country_code":"IN","type":"education","lineage":["https://openalex.org/I74319210"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Puneet Bawa","raw_affiliation_strings":["Chitkara University Institute of Engineering & Technology, Chitkara University,Centre of Excellence for Speech and Multimodal Laboratory,Punjab,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chitkara University Institute of Engineering & Technology, Chitkara University,Centre of Excellence for Speech and Multimodal Laboratory,Punjab,India","institution_ids":["https://openalex.org/I74319210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072742671","display_name":"Virender Kadyan","orcid":"https://orcid.org/0000-0001-8708-9738"},"institutions":[{"id":"https://openalex.org/I5847235","display_name":"University of Petroleum and Energy Studies","ror":"https://ror.org/04q2jes40","country_code":"IN","type":"education","lineage":["https://openalex.org/I5847235"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Virender Kadyan","raw_affiliation_strings":["University of Petroleum & Energy Studies, Energy Acres, Bidholi,Machine Intelligence Research Centre, School of Computer Science,Dehradun,Uttarakhand,India,248007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Petroleum & Energy Studies, Energy Acres, Bidholi,Machine Intelligence Research Centre, School of Computer Science,Dehradun,Uttarakhand,India,248007","institution_ids":["https://openalex.org/I5847235"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034093429","display_name":"Gunjan Chhabra","orcid":"https://orcid.org/0000-0003-4459-7921"},"institutions":[{"id":"https://openalex.org/I60054993","display_name":"Graphic Era University","ror":"https://ror.org/03wqgqd89","country_code":"IN","type":"education","lineage":["https://openalex.org/I60054993"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gunjan Chhabra","raw_affiliation_strings":["Graphic Era Hill University; Graphic Era Deemed to be University,Department of Computer Science and Engineering,Dehradun,Uttarakhand,248007"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graphic Era Hill University; Graphic Era Deemed to be University,Department of Computer Science and Engineering,Dehradun,Uttarakhand,248007","institution_ids":["https://openalex.org/I60054993"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6701998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9948999881744385,"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/T11309","display_name":"Music and Audio Processing","score":0.9477999806404114,"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":0.9114141464233398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251573801040649},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7211594581604004},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6259902119636536},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.595419704914093},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.498917818069458},{"id":"https://openalex.org/keywords/generative-adversarial-network","display_name":"Generative adversarial network","score":0.4712828993797302},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.43060046434402466},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3418322205543518},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15641972422599792},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.14793738722801208}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9114141464233398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251573801040649},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7211594581604004},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6259902119636536},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.595419704914093},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.498917818069458},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.4712828993797302},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.43060046434402466},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3418322205543518},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15641972422599792},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14793738722801208}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt61001.2024.10724686","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt61001.2024.10724686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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":21,"referenced_works":["https://openalex.org/W96321435","https://openalex.org/W2905083703","https://openalex.org/W2963321191","https://openalex.org/W2964069186","https://openalex.org/W2992384298","https://openalex.org/W3097649098","https://openalex.org/W3187713544","https://openalex.org/W3210685431","https://openalex.org/W4281822368","https://openalex.org/W4283161703","https://openalex.org/W4298139897","https://openalex.org/W4303646610","https://openalex.org/W4320490631","https://openalex.org/W4385800847","https://openalex.org/W4387934967","https://openalex.org/W4389610419","https://openalex.org/W4390120075","https://openalex.org/W4390604258","https://openalex.org/W4390873340","https://openalex.org/W6631362777","https://openalex.org/W6908619222"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2888032422","https://openalex.org/W2996316059","https://openalex.org/W4385421777","https://openalex.org/W4377980832","https://openalex.org/W2897769091","https://openalex.org/W2845413374","https://openalex.org/W3005996785","https://openalex.org/W4297411772","https://openalex.org/W4235873501"],"abstract_inverted_index":{"The":[0,24,51,122,132,180],"use":[1,25],"of":[2,26,53,68,112,147,160,189,199],"Generative":[3,86],"Adversarial":[4,87],"Networks":[5,88],"(GANs)":[6,89],"has":[7,16,182],"been":[8,17,100],"increasing":[9],"in":[10,31,38,73,138,193,203],"speech":[11,32,40,92],"recognition":[12],"tasks":[13],"but":[14],"there":[15],"significant":[18,44],"hurdle":[19,45],"due":[20,63],"to":[21,47,64,90,108,154,195],"limited":[22,48,66,113],"availability.":[23,50],"GAN":[27],"have":[28,99],"shown":[29],"promise":[30],"synthesis":[33],"tasks,":[34],"yet":[35],"their":[36],"application":[37],"low-resource":[39,118],"systems":[41,59],"faces":[42,60],"a":[43,65,135],"owing":[46],"data":[49,114],"progress":[52],"effective":[54],"Automatic":[55],"Speech":[56],"Recognition":[57],"(ASR)":[58],"multiple":[61],"challenges":[62],"range":[67],"options":[69],"and":[70,76,96,120,129,166,175],"scarcity,":[71],"resulting":[72],"decreased":[74],"adaptability":[75],"efficiency.":[77],"This":[78,152],"article":[79],"proposes":[80],"an":[81,155],"innovative":[82],"approach":[83],"for":[84,93,105,117,172],"integrating":[85],"create":[91],"both":[94,127],"adults":[95],"children.":[97,121],"Experiments":[98],"conducted":[101,125],"on":[102,186],"using":[103,200],"Mel-Spectrograms":[104],"synthetic":[106],"augmentation":[107,202],"address":[109],"the":[110,139,145,148,173,187,196],"problem":[111],"availability,":[115],"particularly":[116,192],"languages":[119],"experiments":[123],"were":[124],"under":[126],"matched":[128],"mismatched":[130],"conditions.":[131],"results":[133],"demonstrate":[134],"noteworthy":[136],"decrease":[137],"Word":[140],"Error":[141],"Rate":[142],"(WER),":[143],"showcasing":[144],"potential":[146,197],"GAN-based":[149,201],"Vocoder":[150],"model.":[151],"leads":[153],"overall":[156],"Relative":[157],"Improvement":[158],"(RI)":[159],"$\\mathbf{1":[161,167],"2.":[162],"7":[163],"4":[164],"\\%}$":[165,171],"3.":[168],"9":[169],"5":[170],"adult":[174],"children":[176],"ASR":[177,190],"system,":[178],"respectively.":[179],"research":[181],"yielded":[183],"useful":[184],"insights":[185],"advancement":[188],"systems,":[191],"relation":[194],"benefits":[198],"real-world":[204],"scenarios.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}