Unsupervised Prosodic Labeling of Speech Synthesis Databases Using Context-Dependent HMMs

Chen-Yu YANG  Zhen-Hua LING  Li-Rong DAI  

IEICE TRANSACTIONS on Information and Systems   Vol.E97-D   No.6   pp.1449-1460
Publication Date: 2014/06/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E97.D.1449
Type of Manuscript: Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Speech Synthesis and Related Topics
speech synthesis,  prosodic labeling,  hidden Markov model,  prosodic phrase boundary,  emphasis expression,  

Full Text: PDF>>
Buy this Article

In this paper, an automatic and unsupervised method using context-dependent hidden Markov models (CD-HMMs) is proposed for the prosodic labeling of speech synthesis databases. This method consists of three main steps, i.e., initialization, model training and prosodic labeling. The initial prosodic labels are obtained by unsupervised clustering using the acoustic features designed according to the characteristics of the prosodic descriptor to be labeled. Then, CD-HMMs of the spectral parameters, F0s and phone durations are estimated by a means similar to the HMM-based parametric speech synthesis using the initial prosodic labels. These labels are further updated by Viterbi decoding under the maximum likelihood criterion given the acoustic feature sequences and the trained CD-HMMs. The model training and prosodic labeling procedures are conducted iteratively until convergence. The performance of the proposed method is evaluated on Mandarin speech synthesis databases and two prosodic descriptors are investigated, i.e., the prosodic phrase boundary and the emphasis expression. In our implementation, the prosodic phrase boundary labels are initialized by clustering the durations of the pauses between every two consecutive prosodic words, and the emphasis expression labels are initialized by examining the differences between the original and the synthetic F0 trajectories. Experimental results show that the proposed method is able to label the prosodic phrase boundary positions much more accurately than the text-analysis-based method without requiring any manually labeled training data. The unit selection speech synthesis system constructed using the prosodic phrase boundary labels generated by our proposed method achieves similar performance to that using the manual labels. Furthermore, the unit selection speech synthesis system constructed using the emphasis expression labels generated by our proposed method can convey the emphasis information effectively while maintaining the naturalness of synthetic speech.