Abstract
As speech I/O technology develops and improves, there is an increased need for standardized methods to systematically assess the performance of these systems. At the present time, speech synthesis and speech recognition technologies are at different levels of maturation and, accordingly, the procedures for testing the performance of these systems are at different stages of development. In the present paper, we describe the results of testing several text-to-speech systems using traditional intelligibility measures. In addition, we outline the design and philosophy of an automated testing procedure for measuring the performance of isolated utterance speaker-dependent speech recognition systems.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
