Dataset Groups Activity Stream CSTR VCTK Corpus The CSTR VCTK Corpus is a dataset of speech recordings of 109 speakers, each with 20 utterances. BibTex: @dataset{J_Yamagishi_and_C_Veaux_and_K_MacDonald_2024, abstract = {The CSTR VCTK Corpus is a dataset of speech recordings of 109 speakers, each with 20 utterances.}, author = {J. Yamagishi and C. Veaux and K. MacDonald}, doi = {10.57702/k77il7o6}, institution = {No Organization}, keyword = {'Audio', 'CSTR VCTK Corpus', 'Multi-Speaker', 'Recognition', 'Speech', 'Speech Recognition', 'Speech Synthesis', 'VCTK', 'VCTK Corpus', 'Voice Cloning', 'multi-speaker', 'multi-speaker corpus', 'speech synthesis', 'voice cloning'}, month = {dec}, publisher = {TIB}, title = {CSTR VCTK Corpus}, url = {https://service.tib.eu/ldmservice/dataset/cstr-vctk-corpus}, year = {2024} }
