Interspeech'2005 - Eurospeech

Lisbon, Portugal
September 4-8, 2005

On Building a Concatenative Speech Synthesis System from the Blizzard Challenge Speech Databases

Wael Hamza (1), Raimo Bakis (1), Zhi Wei Shuang (2), Heiga Zen (3)

(1) IBM T.J. Watson Research Center, Yorktown Heights, NY, USA; (2) IBM China Research Lab, China; (3) Nagoya Institute of Technology, Japan

In this paper, we compare two methods of building a concatenative speech synthesis system from the relatively small, "Blizzard Challenge" speech databases. In the first method we build a system directly from the Blizzard databases using the IBM Concatenative Speech Synthesis System originally designed for very large speech databases. In the second method, a larger database is used to build the synthesis system and the output is "morphed" to match the speakers in the Blizzard databases. The second method outperformed the first while maintaining the identity of the Blizzard target speakers.

Full Paper

Bibliographic reference.  Hamza, Wael / Bakis, Raimo / Shuang, Zhi Wei / Zen, Heiga (2005): "On building a concatenative speech synthesis system from the blizzard challenge speech databases", In INTERSPEECH-2005, 97-100.