A small footprint hybrid statistical and unit selection text-to-speech synthesis system for Turkish

Abstract

Unit selection based text-to-speech synthesis (TTS) can generate high quality speech. However, The HMM-based text-to-speech (HTS) has also advantages such as the lack of spurious errors that are observed in the unit selection scheme. Another advantage is the small memory footprint requirement. Here, we propose a novel hybrid statistical/unit selection TTS system for agglutinative languages that aims at improving the quality of the baseline HTS system while keeping the memory footprint small. Listeners preferred the hybrid system over a state-of-the-art HTS baseline system in the A/B preference tests.