A new HMM-based speech synthesis system for Slovenian language is presented. The quality of synthesized speech has been assessed by subjective and objective tests. The results show that the new system outperforms our previously developed diphone-based waveform concatenation synthesizer in terms of naturalness and general impression. © Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
Vesnicer, B., & Mihelič, F. (2004). Evaluation of the Slovenian HMM-based speech synthesis system. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 3206, pp. 513–520). Springer Verlag. https://doi.org/10.1007/978-3-540-30120-2_65
Mendeley helps you to discover research relevant for your work.