Toward the use of information density based descriptive features in HMM based speech synthesis

Over the last decades, acoustic modeling for speech synthesis has been improved significantly. However, in most systems, the descriptive feature set used to represent annotated text has been the same for many years. Specifically, the prosody models in most systems are based on low level information such as syllable stress or word part-of-speech tags. In this paper, we propose to enrich the descriptive feature set by adding a linguistic measure computed from the predictability of an event, such as the occurrence of a syllable or word. By adding such descriptive features, we assume that we will improve prosody modeling. This new feature set is then used to train prosody models for speech synthesis. Results from an evaluation study indicate a preference for the new descriptive feature set over the conventional one.