A small footprint hybrid statistical/unit selection text-to-speech synthesis system for agglutinative languages

Abstract

Despite its success, unit selection based text-to-speech synthesis (TTS) has has some disadvantages such as sudden discontinuities in speech that distract the listeners. The HMM-based TTS (HTS) approach has been increasingly getting more attention from the TTS research community. One of the advantage is the lack of spurious errors that are observed in the unit selection scheme. Another advantage of the HTS system is the small memory footprint requirement which makes it attractive for embedded devices. 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. The intelligibility and quality scores of the baseline system are comparable to the MOS scores of English reported in the Blizzard Challenge tests. Listeners preferred the hybrid system over the baseline system in the A/B preference tests.