… algorithm in both Text-To-Speech (TTS) synthesis and cross-lingual voice transformation
applications. Experimental results show that the proposed trajectory tiling approach can render …

… Text-to-speech (TTS) synthesis systems can roughly be divided into two main approaches:
1) statistical parametric speech … Both of these two approaches have their own pros and cons. …

… to tile (approximate) the generated trajectory. An HMM trajectory tiling (HTT) based approach
to … The feature parameter trajectories generated by the improved HMMs trained in MGE are …

… The corresponding speech technologies consist of text-to-speech (TTS), voice transformation
from one speaker to another speaker in the same language, or translating from one …

… a trajectory tiling method guided by deep neural networks (DNNs) for text-to-speech (TTS), …
from the database using a trajectory tiling method. Experiments demonstrate that, under the …

… the last step, converts the trajectories of model parameters into output speech. Let us also
note that the trajectories generated by the HMM can also be used in the SUI method (\(\hbox {F…

… A brief overview of various approaches to text-to-speech is given with more detail provided
for … feature trajectories can be modeled without using the conventional dynamic features. …

… -based approaches have been suggested in recent years for converting text to speech …
Lu, and FK Soong, “A new high quality trajectory tiling based hybrid TTS in real time,” in Proc…

… ‘trajectory tiling’ was coined by them and featured in their 2010 entry to the Challenge (Qian
et al., 2010). It alludes to a method … (the ‘trajectory’), whilst the overlayed samples (‘tiles’) pro…

… used in text-to-speech synthesis. In addition, synthesising news using textto-speech is more
… A unified trajectory tiling approach to high quality speech rendering. IEEE transactions on …