Shinji Takaki

An autoregressive recurrent mixture density network for parametric speech synthesis

2017

Neural-network-based generative models, such as mixture density networks, are potential solutions for speech synthesis. In this paper we follow this path and propose a recurrent mixture density network that incorporates a trainable autoregressive model. An …

Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism

2021 · arXiv (Cornell University)

This paper proposes a novel Sequence-to-Sequence (Seq2Seq) model integrating the structure of Hidden Semi-Markov Models (HSMMs) into its attention mechanism. In speech synthesis, it has been shown that methods based on Seq2Seq models using deep …