← Search

Mirjam Wester

1 accepted papers

2016

Robust TTS duration modelling using DNNS

ICASSP 2016accepted

Accurate modelling and prediction of speech-sound durations is an important component in generating more natural synthetic speech. Deep neural networks (DNNs) offer a powerful modelling paradigm, and large, found corpora of natural and expressive speech are easy to acquire for training them. Unfortu…

Cited by 0SourceScholar