Author:Govender, Avashna; Nouhou, B; De Wet, FebeDate:Nov 2015Acquiring large amounts of child speech data is a particularly difficult task. One could therefore consider the possibility to add existing corpora of child speech data to the severely limited resources that are available for developing child ...Read more
Author:Louw, Johannes ADate:Dec 2019Recent work in sequence-to-sequence neural networks with attention mechanisms, such as the Tacotron 2 and DCTTS architectures, have brought on substantial naturalness improvements in synthesised speech. These architectures require at least ...Read more
Author:Louw, Johannes ADate:Dec 2020Sequence-to-sequence end-to-end models for text-to-speech have shown significant gains in naturalness of the produced synthetic speech. These models have an encoder-decoder architecture, without an explicit duration model, but rather a learned ...Read more