论文信息 - On building a concatenative speech synthesis system from the blizzard challenge speech databases

On building a concatenative speech synthesis system from the blizzard challenge speech databases

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 Concatenetative 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.

Heiga Zen | Zhiwei Shuang | Raimo Bakis | Wael Hamza

[1] Hideki Kawahara,et al. Restructuring speech representations using a pitch-adaptive time-frequency smoothing and an instantaneous-frequency-based F0 extraction: Possible role of a repetitive structure in sounds , 1999, Speech Commun..

[2] Raimo Bakis,et al. Reconciling pronunciation differences between the front-end and the back-end in the IBM speech synthesis system , 2004, INTERSPEECH.

[3] Eric Moulines,et al. Pitch-synchronous waveform processing techniques for text-to-speech synthesis using diphones , 1989, Speech Commun..

[4] Mahesh Viswanathan,et al. Recent improvements to the IBM trainable speech synthesis system , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[5] Christina L. Bennett. Large scale evaluation of corpus-based synthesizers: results and lessons from the blizzard challenge 2005 , 2005, INTERSPEECH.