Segmental intelligibility of synthetic speech produced by eight text‐to‐speech systems

Abstract

Several studies measuring the segmental intelligibility of eight text‐to‐speech systems and a natural speech control using the modified rhyme test (MRT) have been conducted in the Speech Research Laboratory. Results indicated that the voices tested could be grouped into four categories: natural speech, high‐quality synthetic speech, moderate‐quality synthetic speech, and low‐quality synthetic speech. The overall performance of the best system, DECtalk‐Paul, was equivalent to natural speech only in terms of performance on initial consonants. The findings from these laboratory studies will be discussed in terms of recent work investigating the perception of synthetic speech under more severe conditions. Additional results obtained using a variation of the standard MRT will be presented. Suggestions for future research on improving the quality of synthetic speech will be discussed. [Work supported, in part, by NIH and AFOSR.]