Abstract—A new Mexican Spanish voice was created using 4 festival modules (Clunits, Clustergen,Multisyn and HTS), as well as an additional database was created with Straight processing. All voices were created using the same database to allow for consistency and for easier comparison of the output. Once these voices have been created they can be used as a baseline for further development in Mexican Spanish speech synthesis. Except for the Multisyn module, which has some problems due to coverage, results are acceptable, with the HMM designed voices having the best quality.

Index Terms—Speech synthesis, straight, festival.

The authors are with the Universidad Nacional Autonoma de Mexico(UNAM) (e-mail: abelhc@hotmail.com).

Cite: Abel Herrera Camacho and Fernando Del Rio Ávila, "Development of a Mexican Spanish Synthetic Voice Using Synthesizer Modules of Festival Speech and HTS-Straight," International Journal of Computer and Electrical Engineering vol. 5, no. 1, pp. 36-39, 2013.