Automatically-determined Unit Inventories for Unit Selection Text-to-Speech Synthesis

Speech synthesis - the generation of speech by computer - is a key technology for mobile computing and telephone-based services. A recent development, called Unit selection speech synthesis has now improved the quality of the speech so much that it is often indistinguishable from natural speech.Unfortunately, the creation of new voices for this unit selection technology is very expensive because it is labour intensive and must be done by experts. This is preventing the use of the technology in many applications, such as the production of high quality speech synthesisers for languages spoken in less developed countries.We are proposing to develop methods that will make it much quicker and cheaper to create new voices for speech synthesisers and also allow non-experts to carry out this work.