The IBM Submission to the 2006 Blizzard Text-to-Speech Challenge
Ellen Eide, Raul Fernandez, Ron Hoory, Wael Hamza, Zvi Kons, Michael Picheny, Ariel Sagi, Slava Shechtman, Zhi Wei Shuang · 2006
In this paper, we present two concatenative text-to-speech systems built from the “Blizzard Challenge ” speech databases. The two systems differ primarily in their segment selection cost function. One system has our baseline cost function, and the other has a cost function which has been altered to potentially better handle small datasets. Results indicate that both systems perform similarly in terms of MOS and intelligibility. 1.