F. del Ro and A. Herrera (Mexico)
Acoustic, Speech Processing and Applications; SpeechSynthesis; Diphones; Time Domain Pitch SynchronousOverlap Add.
We reported a Mexican Spanish synthesizer using concatenate diphones technique. The diphones are from an adult male with accent from the central region of Mexico. We used only 29 phonemes (we used 2 sets of vowels), and approximately 500 diphones. The database was design to use a small quantity of memory, to avoid the need of compressing or coding the original segments, which increases speech clarity. Grammatical rules help us design the syllable emphasis, and no special words pronunciation is needed. A simple software running under Windows was designed to write constrain-free text in a window. We have now added a PSOLA processing to improve the naturalness. The results report a natural speech, with small disadvantages compared to other more complicated international systems for Spanish, however these systems are not addressed for Mexican Spanish.
Important Links:
Go Back
