{"id":"https://openalex.org/W7119480141","doi":"https://doi.org/10.1007/s10772-025-10241-w","title":"STFT-GradTTS: a robust, diffusion-based speech synthesis system with iSTFT decoder for Bangla","display_name":"STFT-GradTTS: a robust, diffusion-based speech synthesis system with iSTFT decoder for Bangla","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119480141","doi":"https://doi.org/10.1007/s10772-025-10241-w"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-025-10241-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-025-10241-w","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10772-025-10241-w","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122331764","display_name":"Mushahid Intesum","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Mushahid Intesum","raw_affiliation_strings":["University of Dhaka, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Dhaka, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122324700","display_name":"Abdullah Ibne Masud","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Abdullah Ibne Masud","raw_affiliation_strings":["University of Dhaka, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Dhaka, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061212339","display_name":"Rezaul Karim","orcid":"https://orcid.org/0000-0002-8453-1604"},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Md. Rezaul Karim","raw_affiliation_strings":["University of Dhaka, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Dhaka, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I205746353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122400166","display_name":"Md. Ashraful Islam","orcid":null},"institutions":[{"id":"https://openalex.org/I205746353","display_name":"University of Dhaka","ror":"https://ror.org/05wv2vq37","country_code":"BD","type":"education","lineage":["https://openalex.org/I205746353"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Md. Ashraful Islam","raw_affiliation_strings":["University of Dhaka, Dhaka, Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Dhaka, Dhaka, Bangladesh","institution_ids":["https://openalex.org/I205746353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5122400166"],"corresponding_institution_ids":["https://openalex.org/I205746353"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04327917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9004999995231628,"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":0.9004999995231628,"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/T13194","display_name":"ICT in Developing Communities","score":0.01360000018030405,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.009399999864399433,"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/bengali","display_name":"Bengali","score":0.8337000012397766},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.671999990940094},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6244999766349792},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5558000206947327},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.41350001096725464},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.40299999713897705},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.37880000472068787},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.367900013923645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9006999731063843},{"id":"https://openalex.org/C19235068","wikidata":"https://www.wikidata.org/wiki/Q9610","display_name":"Bengali","level":2,"score":0.8337000012397766},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.671999990940094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6377000212669373},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6244999766349792},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45239999890327454},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.40299999713897705},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-025-10241-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-025-10241-w","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10772-025-10241-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-025-10241-w","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5263964533805847,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1901129140","https://openalex.org/W2007321142","https://openalex.org/W2120847449","https://openalex.org/W2471520273","https://openalex.org/W2598638573","https://openalex.org/W2889724045","https://openalex.org/W2895654193","https://openalex.org/W2903739847","https://openalex.org/W2939803434","https://openalex.org/W2963341956","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W3037038648","https://openalex.org/W3095199334","https://openalex.org/W3095410713","https://openalex.org/W3215615641","https://openalex.org/W4210287297","https://openalex.org/W4372270423","https://openalex.org/W4391021721","https://openalex.org/W4406461672"],"related_works":[],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1,193],"synthesis":[2,123],"is":[3],"a":[4,50,94,100,105,187,198],"critical":[5],"area":[6],"in":[7,15,40,138,150,175,204],"speech":[8,42,139,176,207],"and":[9,20,77,104,153,166,179],"language":[10,31,206],"processing,":[11],"with":[12],"extensive":[13],"applications":[14],"assistive":[16],"technologies,":[17],"virtual":[18],"assistants,":[19],"automated":[21],"content":[22],"generation.":[23],"Despite":[24],"Bangla":[25,41,54,191],"being":[26],"the":[27,88,135,172],"seventh":[28],"most":[29],"spoken":[30],"globally,":[32],"high-quality":[33],"TTS":[34,97],"datasets":[35],"remain":[36],"scarce,":[37],"limiting":[38],"advancements":[39],"synthesis.":[43,208],"To":[44],"bridge":[45],"this":[46],"gap,":[47],"we":[48,90],"introduce":[49],"meticulously":[51],"curated":[52],"single-speaker":[53],"audio":[55,154],"dataset":[56,65],"comprising":[57],"over":[58],"20":[59],"hours":[60],"of":[61,147],"clean":[62],"speech.":[63],"Our":[64,182],"ensures":[66],"diverse":[67],"linguistic":[68],"coverage,":[69],"incorporating":[70],"compound":[71],"letters,":[72],"long":[73],"vowels,":[74],"Sanskrit":[75],"words,":[76],"varied":[78],"sentence":[79],"structures":[80],"while":[81],"maintaining":[82],"phonetic":[83],"balance.":[84],"In":[85],"addition":[86],"to":[87],"dataset,":[89],"propose":[91],"STFT-GradTTS":[92,169],",":[93],"novel":[95],"diffusion-based":[96],"model":[98],"featuring":[99],"Multi-Stream":[101],"iSTFT":[102],"decoder":[103,112],"Stochastic":[106],"Duration":[107],"Predictor":[108],"(SDP).":[109],"The":[110,128],"iSTFT-based":[111],"synthesizes":[113],"high-fidelity":[114],"waveforms":[115],"by":[116],"decomposing":[117],"signals":[118],"into":[119],"sub-bands":[120],"using":[121],"learnable":[122],"filters,":[124],"enhancing":[125],"spectral":[126],"clarity.":[127],"SDP":[129],"models":[130,174],"phoneme":[131],"duration":[132,151,180],"distributions,":[133],"capturing":[134],"natural":[136],"variability":[137],"pacing.":[140],"Together,":[141],"these":[142],"innovations":[143],"address":[144],"key":[145],"limitations":[146],"GradTTS,":[148],"particularly":[149],"accuracy":[152],"naturalness.":[155],"We":[156],"validate":[157],"our":[158],"approach":[159],"through":[160],"blind":[161],"subjective":[162],"&":[163],"objective":[164],"evaluations":[165],"demostrate":[167],"that":[168],"significantly":[170],"outperforms":[171],"baseline":[173],"quality,":[177],"naturalness,":[178],"modeling.":[181],"work":[183],"not":[184],"only":[185],"establishes":[186],"new":[188],"benchmark":[189],"for":[190,201],"Text-to-Speech":[192],"systems":[194],"but":[195],"also":[196],"provides":[197],"solid":[199],"foundation":[200],"future":[202],"research":[203],"low-resource":[205]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-01-09T00:00:00"}
