Objective Intelligibility Assessment Of Text-To-Speech System Using Template Constrained Generalized Posterior Probability

Speech intelligibility is one of the most important measures in evaluating text-to-speech (US) synthesizer. In this paper, we propose an automatic objective intelligibility measure for evaluating synthesized speech using template constrained generalized posterior probability (TCGPP). TCGPP is a posterior probability based confidence measure, which has the advantage to identify small granularity errors in synthesized speech. Moreover, the TCGPP scores over a test set can be summarized into an overall objective intelligibility score to compare two synthesizers, or rank multiple TTS systems. We conducted the experiments using the synthesized test sentences from all the participants of EH1 English task in Blizzard Challenge 2010. The results show the proposed measure has high correlation (corr = 0.9) with subjective scores and ranking.