Speech and Vision Lab

The size of unit selection speech synthesis is between few hundred of MBs to GBs. Such a huge database requires a large memory size and slows down the computational speed. It also causes too much hindrance to download and install in ordinary machines. To some, it may look old-fashioned to worry about size and speed of a software application. With ever-increasing CPU speed and disk sizes growing continuously, many have forgotten what it is like to be restricted in memory and computational complexity. However, to those wishing to make speech applications ubiquitous, it quickly becomes clear that not all applications are deployed in resource-rich environments, with lots of CPU cycles to burn and large amount of memory and storage. In this paper we propose three methods for pruning large unit selection databases to be able to deploy in practical applications. All these techniques are evaluated using objective measures.