Title :
Probability based prosody model for unit selection
Author :
Ma, Xijun ; Zhang, Wei ; Zhu, Weibin ; Shi, Qin ; Jin, Ling
Author_Institution :
IBM China Res. Lab, China
Abstract :
Most modern text-to-speech (TTS) systems are unit selection style. In this kind of system, the predicted prosody values, such as pitch, duration and energy values for each synthesis unit, are important factors to conduct unit selection. We present a probability based prosody model in which the distribution of prosody values in a given context equivalent cluster is described by a Gaussian mixture model (GMM), and the distance between a candidate unit and the context equivalent cluster is defined by the GMM probability output. A novel framework for unit selection style TTS systems is derived from the model, and a series of experiments are done on the framework.
Keywords :
Gaussian processes; speech synthesis; statistical distributions; GMM probability output; Gaussian mixture model; TTS systems; context equivalent cluster; probability distribution; prosody model; text-to-speech systems; unit selection style; Context modeling; Fuzzy systems; Predictive models; Probability distribution; Speech synthesis; Statistics; Text analysis;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Print_ISBN :
0-7803-8484-9
DOI :
10.1109/ICASSP.2004.1326069