Optimal weight tuning method for unit selection cost functions in syllable based text-to-speech synthesis

This paper proposes a method for tuning the weights of unit selection cost functions in syllable based text-to-speech (TTS) synthesis system. In this work, unit selection cost functions, namely target cost and concatenation cost, are designed appropriate to syllables. The method tunes the weights in such a way that perceptual preference patterns are appropriately considered while selecting the units. The method uses genetic algorithm to derive the optimal weights. Fitness function is designed to map perceptual preference patterns into weights of unit selection cost functions. The effectiveness of proposed method is evaluated by both subjective and objective measures. From the results, it is observed that the derived optimal weights can synthesize good quality speech compared to manually tuned weights.

Figure optionsDownload as PowerPoint slideHighlights
► Weights of unit selection cost functions are tuned based on perceptual preference patterns of listeners.
► Genetic algorithm is used to derive optimal weights.
► Fitness function is designed to map perceptual preference patterns into weights of unit selection cost functions.
► The derived optimal weights can synthesize a good quality speech compared to manually tuned weights.