Igor Jauk, Antonio Bonafonte, Paula Lopez-Otero, Laura Docío Fernández. Creating expressive synthetic voices by unsupervised clustering of audiobooks. In INTERSPEECH 2015, 16th Annual Conference of the International Speech Communication Association, Dresden, Germany, September 6-10, 2015. pages 3380-3384, ISCA, 2015. [doi]
Abstract is missing.