Dataset Groups Activity Stream VCTK Corpus The VCTK corpus is an English multi-speaker dataset, with 44 hours of audio spoken by 109 native English speakers. BibTex: @dataset{Christophe_Veaux_and_Junichi_Yamagishi_and_Kirsten_MacDonald_2024, abstract = {The VCTK corpus is an English multi-speaker dataset, with 44 hours of audio spoken by 109 native English speakers.}, author = {Christophe Veaux and Junichi Yamagishi and Kirsten MacDonald}, doi = {10.57702/bw3hjwag}, institution = {No Organization}, keyword = {'Audio', 'Corpus', 'Speaker Recognition', 'Speech', 'Speech Processing', 'Speech Synthesis', 'VCTK', 'Voice Cloning', 'Voice Conversion'}, month = {dec}, publisher = {TIB}, title = {VCTK Corpus}, url = {https://service.tib.eu/ldmservice/dataset/vctk-corpus}, year = {2024} }
