@inproceedings{oai:nitech.repo.nii.ac.jp:00003453, author = {Lu, Heng and Wu, Yi Jian and Tokuda, Keiichi and Dai, Li Rong and Wang, Ren hua}, book = {ICASSP 2009. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009.}, month = {Apr}, note = {application/pdf, This paper proposes a state duration modeling method using full covariance matrix for HMM-based speech synthesis. In this method, a full covariance matrix instead of the conventional diagonal covariance matrix is adopted in the multi-dimensional Gaussian distribution to model the state duration of each context-dependent phoneme. At synthesis stage, the state durations are predicted using the clustered context-dependent distributions with full covariance matrices. Experimental results show that the synthesized speech using full-covariance state duration models is more natural than the conventional method when we change the speaking rate of synthesized speech.}, pages = {4033--4036}, publisher = {Institute of Electrical and Electronics Engineers}, title = {Full Covariance State Duration Modeling for HMM-Based Speech Synthesis}, year = {2009} }