An implementation of decision tree-based context clustering on graphics processing units

Decision tree-based context clustering is essential but timeconsuming while building HMM-based speech synthesis systems. Its widely used implementation is not designed to take advantage of highly parallel architectures, such as GPUs. This paper shows an implementation of tree-based clustering for these highly parallel architectures. Experimental results showed that the new implementation running on GPUs was significantly faster than the conventional one running on CPUs.