Limited Domain Synthesis

摘要

This work presents a reliable and efficient mehtod for building limited domain speech synthesis voices. By constructing databases close to the targeted domain of the speech application, unit selection synthesis techniques can be used to reliably give very hihg quality synthesis within domain. In addition to a high quality result we include the techniques and processes required to build such voices often allowing new voices in limited but quite compelx domains such as dialog systems to be created in under a week. The full tools, documentation examples etc are available for free at http://festvox.org.