Third International Conference on Spoken Language Processing (ICSLP 94)

Yokohama, Japan
September 18-22, 1994

Generation of Multi-Syllable Nonsense Words for the Assessment of Korean Text-To-Speech System

Cheol-Woo Jo (1), Kyung-Tae Kim (2), Yong-Ju Lee (3)

(1) Acoustic and Speech Group, Department of Control and Instrumentation Eng., Changwon National University, Kyeongnam, Korea
(2) Department of Information and Communication Eng., Hannam University, Taejon, Korea
(3) Department of Computer Eng., Wonkwang University, Jeonpuk, Korea

In this paper we propose a method to generate a multisyllable nonsense word set for the purpose of synthetic speech assessment and applies the wordset to assess one commercial text-to-speech system. Some results about the experiment is suggested and it is verified that the generated nonsense wordset can be used to assess the intelligibility of the synthesizer in phoneme level or in phonemic environmental level. From the experimental results it is verified that such multi-syllable nonsense wordset can be useful for the assessment of synthesized speech.

Full Paper

Bibliographic reference.  Jo, Cheol-Woo / Kim, Kyung-Tae / Lee, Yong-Ju (1994): "Generation of multi-syllable nonsense words for the assessment of Korean text-to-speech system", In ICSLP-1994, 1255-1258.