Limited Domain Synthesis
Abstract
This work presents a reliable and efficient method 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 high 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 complex domains such as dialog systems to be created in under a week.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 01, 2000
- Accession Number
- ADA461150
Entities
People
- Alan W. Black
- Kevin A. Lenzo
Organizations
- Carnegie Mellon University