ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Multi-centroidal duration generation algorithm for HMM-based TTS

Yongguo Kang, Jian Li, Yan Deng, Miaomiao Wang

A novel method is proposed to improve the duration prediction for HMM based speech synthesis. Based on the decision tree trained by the conventional HTS training method, the duration instances of every leaf node are further clustered into several classes by the K-means clustering method, and the mapping functions between the context features and class labels are trained by CRF. Instead of using the mean value of the Gaussian distribution of a leaf node in the decision tree as the predicted duration, the weighted summation of the multi-centroids from these several clustered classes is used to predict the phoneme duration. The weights are given by the output probability provided by CRF according to input context features and the prior probability from the clustering results. Compared with conventional HTS method, experiments show that the proposed method can significantly reduce RMSE in objective evaluations and achieves better preference scores in the subjective evaluations.

doi: 10.21437/Interspeech.2013-390

Cite as: Kang, Y., Li, J., Deng, Y., Wang, M. (2013) Multi-centroidal duration generation algorithm for HMM-based TTS. Proc. Interspeech 2013, 1540-1543, doi: 10.21437/Interspeech.2013-390

  author={Yongguo Kang and Jian Li and Yan Deng and Miaomiao Wang},
  title={{Multi-centroidal duration generation algorithm for HMM-based TTS}},
  booktitle={Proc. Interspeech 2013},