{"@context":{"@language":"en","@vocab":"https://schema.org/","citeAs":"cr:citeAs","column":"cr:column","conformsTo":"dct:conformsTo","cr":"http://mlcommons.org/croissant/","rai":"http://mlcommons.org/croissant/RAI/","data":{"@id":"cr:data","@type":"@json"},"dataType":{"@id":"cr:dataType","@type":"@vocab"},"dct":"http://purl.org/dc/terms/","examples":{"@id":"cr:examples","@type":"@json"},"extract":"cr:extract","field":"cr:field","fileProperty":"cr:fileProperty","fileObject":"cr:fileObject","fileSet":"cr:fileSet","format":"cr:format","includes":"cr:includes","isLiveDataset":"cr:isLiveDataset","jsonPath":"cr:jsonPath","key":"cr:key","md5":"cr:md5","parentField":"cr:parentField","path":"cr:path","recordSet":"cr:recordSet","references":"cr:references","regex":"cr:regex","repeated":"cr:repeated","replace":"cr:replace","sc":"https://schema.org/","separator":"cr:separator","source":"cr:source","subField":"cr:subField","transform":"cr:transform","wd":"https://www.wikidata.org/wiki/"},"@type":"sc:Dataset","conformsTo":"http://mlcommons.org/croissant/1.0","name":"BAS4R: A Multi-Condition Bangla Speech Dataset for Gender-Aware Real and Fake Voice Analysis","url":"https://doi.org/10.7910/DVN/YVWOAL","creator":[{"@type":"Person","givenName":"Al Arian","familyName":"Ahmad","affiliation":{"@type":"Organization","name":"https://ror.org/01vxg3438"},"sameAs":"https://orcid.org/0009-0009-6344-0189","@id":"https://orcid.org/0009-0009-6344-0189","identifier":"https://orcid.org/0009-0009-6344-0189","name":"Al Arian Ahmad"},{"@type":"Person","givenName":"Nakib","familyName":"Turzo","affiliation":{"@type":"Organization","name":"https://ror.org/01vxg3438"},"sameAs":"https://orcid.org/0000-0002-4275-2636","@id":"https://orcid.org/0000-0002-4275-2636","identifier":"https://orcid.org/0000-0002-4275-2636","name":"Turzo, Nakib"},{"@type":"Person","givenName":"Kumar","familyName":" Kumar Dutta","affiliation":{"@type":"Organization","name":"https://ror.org/01vxg3438"},"sameAs":"https://orcid.org/0009-0000-1800-7508","@id":"https://orcid.org/0009-0000-1800-7508","identifier":"https://orcid.org/0009-0000-1800-7508","name":"Durjoy Kumar Dutta"},{"@type":"Person","givenName":"Abdul Wadud","familyName":"Wadud","affiliation":{"@type":"Organization","name":"https://ror.org/01vxg3438"},"sameAs":"https://orcid.org/0009-0000-5181-6964","@id":"https://orcid.org/0009-0000-5181-6964","identifier":"https://orcid.org/0009-0000-5181-6964","name":"Wadud, Abdul Wadud"}],"description":"BAS4R is a structured and large-scale Bangla speech dataset developed to support research in replay attack detection and audio spoofing analysis within voice biometric systems. The dataset contains both authentic (real) and systematically manipulated (spoofed) speech recordings collected under controlled and realistic acoustic conditions. The complete dataset comprises 143.88 hours of audio recordings, totaling 120,125 audio files, organized into five major categories: Channel-based: 28,830 files (34.65 hours) Signal Processing-based: 28,830 files (34.53 hours) Effect-based: 28,830 files (34.48 hours) Replay-based: 28,830 files (34.48 hours) Real Data: 4,805 files (5.75 hours) Speech samples were collected from 100 native Bangla speakers (50 male and 50 female) aged 20–26 years, ensuring balanced gender representation and demographic consistency. All recordings were captured in controlled environments and stored in high-quality digital audio format. The dataset follows a structured hierarchical organization separating real and spoofed samples by category and attack condition, facilitating reproducible research. The spoofed data were generated using real signal processing techniques, channel transmission effects, environmental distortions, and replay setups. BAS4R is suitable for research in anti-spoofing systems, speaker verification robustness evaluation, replay attack detection, and deep learning–based audio classification.","keywords":["Computer and Information Science","Engineering"],"license":"http://creativecommons.org/publicdomain/zero/1.0","datePublished":"2026-02-11","dateModified":"2026-02-11","includedInDataCatalog":{"@type":"DataCatalog","name":"Harvard Dataverse","url":"https://dataverse.harvard.edu"},"publisher":{"@type":"Organization","name":"Harvard Dataverse"},"version":"1.0","citeAs":"@data{DVN/YVWOAL_2026,author = {Al Arian Ahmad and Turzo, Nakib and Durjoy Kumar Dutta and Wadud, Abdul Wadud},publisher = {Harvard Dataverse},title = {BAS4R: A Multi-Condition Bangla Speech Dataset for Gender-Aware Real and Fake Voice Analysis},year = {2026},url = {https://doi.org/10.7910/DVN/YVWOAL}}","distribution":[{"@type":"cr:FileObject","@id":"Channel-based.zip","name":"Channel-based.zip","encodingFormat":"application/zip","md5":"785c8fed3f509cbe7e336099c3f78a2b","contentSize":"2307531565","description":"","contentUrl":"https://dataverse.harvard.edu/api/access/datafile/13454317"},{"@type":"cr:FileObject","@id":"Effect-based.zip","name":"Effect-based.zip","encodingFormat":"application/zip","md5":"bd84c6354fba77dd85c9424636cd39de","contentSize":"2650879946","description":"","contentUrl":"https://dataverse.harvard.edu/api/access/datafile/13454315"},{"@type":"cr:FileObject","@id":"Real Data.zip","name":"Real Data.zip","encodingFormat":"application/zip","md5":"88bb090827317d2d4595ad4196aa41d1","contentSize":"2312542676","description":"","contentUrl":"https://dataverse.harvard.edu/api/access/datafile/13454318"},{"@type":"cr:FileObject","@id":"Replay-based.zip","name":"Replay-based.zip","encodingFormat":"application/zip","md5":"6194c0953efa43778671b6ee6a199e3c","contentSize":"2656898557","description":"","contentUrl":"https://dataverse.harvard.edu/api/access/datafile/13454316"},{"@type":"cr:FileObject","@id":"Signal Processing.zip","name":"Signal Processing.zip","encodingFormat":"application/zip","md5":"9a095e9f5385629629e99993895b9a71","contentSize":"2584858383","description":"","contentUrl":"https://dataverse.harvard.edu/api/access/datafile/13454314"}]}