Small Footprint Text-to-Speech Synthesis


Carlos Mendes


  • 15:00, December 5, 2008
  • Room 336



In recent years, TTS systems are developed as an output device of human-machine interfaces, and they are used in many applications such as car navigation systems, information retrieval over telephone, voice mail and so on. Although most acoustical concatenation TTS systems are able to synthesize speech with high quality, they lack in terms of computational performance, mostly due to the large amount of stored speech data.

This work main objective was the development of a small footprint text to speech synthesis system, by using HMM models to generate artificial speech. The developed system was applied for European Portuguese, but is general enough to be applied to other languages.