Improvements to Prosodic Variation in Long Short-Term Memory Based Intonation Models Using Random Forest

摘要

Statistical parametric speech synthesis has overcome unit selection methods in many aspects, including flexibility and variability. However, the intonation of these systems is quite monotonic, especially in case of longer sentences. Due to statistical methods the variation of fundamental frequency (F0) trajectories decreases. In this research a random forest (RF) based classifier was trained with radio conversations based on the perceived variation by a human annotator. This classifier was used to extend the labels of a phonetically balanced, studio quality speech corpus. With the extended labels a Long Short-Term Memory (LSTM) network was trained to model fundamental frequency (F0). Objective and subjective evaluations were carried out. The results show that the variation of the generated F0 trajectories can be fine-tuned with an additional input of the LSTM network.