A survey on neural speech synthesis

X Tan, T Qin, F Soong, TY Liu - ar** architectures suitable for modeling raw audio is a challenging problem due to
the high sampling rates of audio waveforms. Standard sequence modeling approaches like …

Gansynth: Adversarial neural audio synthesis

J Engel, KK Agrawal, S Chen, I Gulrajani… - ar**20a/**20a.pdf" data-clk="hl=ca&sa=T&oi=gga&ct=gga&cd=7&d=15645705670677592172&ei=DKyxZ_C3ArutieoP4ZvliAM" data-clk-atid="bHgNuWm2INkJ" target="_blank">[PDF] mlr.press

Waveflow: A compact flow-based model for raw audio

W **, K Peng, K Zhao, Z Song - … Conference on Machine …, 2020 - proceedings.mlr.press
In this work, we propose WaveFlow, a small-footprint generative flow for raw audio, which is
directly trained with maximum likelihood. It handles the long-range structure of 1-D …

Neural source-filter waveform models for statistical parametric speech synthesis

X Wang, S Takaki, J Yamagishi - IEEE/ACM Transactions on …, 2019 - ieeexplore.ieee.org
Neural waveform models have demonstrated better performance than conventional
vocoders for statistical parametric speech synthesis. One of the best models, called …

[PDF][PDF] A Deep Learning Algorithm for Personalized Blood Glucose Prediction.

T Zhu, K Li, P Herrero, J Chen, P Georgiou - KDH@ IJCAI, 2018 - ceur-ws.org
A convolutional neural network (CNN) model is presented to forecast the future glucose
levels of the patients with type 1 diabetes. The model is a modified version of a recently …