The recurrent neural network (RNN) has been used in audio and speech processing, such as language translation and speech recognition. Although RNN-based architecture can be applied to speech synthesis, the long computing time is still the primary concern. This research proposes a fast gated recurrent neural network, a fast RNN-based architecture, for speech synthesis based on the minimal gated unit (MGU). Our architecture removes the unit state history from some equations in MGU. OurMGU-based architecture is about twice faster, with equally good sound quality than the other MGU-based architectures.
|Number of pages||5|
|Journal||IEICE Transactions on Information and Systems|
|State||Published - Sep 2022|
- acoustic modelling
- gated recurrent neural network
- long short-term memory
- speech synthesis