Deep Learning

【108 話者編】Deep Voice 3: 2000-Speaker Neural Text-to-Speech / arXiv:1710.07654 [cs.SD]
Audio samples: https://r9y9.github.io/deepvoice3_pytorch/
Dec 22, 2017 4 min read
【単一話者編】Deep Voice 3: 2000-Speaker Neural Text-to-Speech / arXiv:1710.07654 [cs.SD]
Audio samples: https://r9y9.github.io/deepvoice3_pytorch/
Dec 13, 2017 3 min read
Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention. [arXiv:1710.08969]
GitHub: https://github.com/r9y9/deepvoice3_pytorch
Nov 23, 2017 3 min read
Tacotron: Towards End-to-End Speech Synthesis / arXiv:1703.10135 [cs.CL]
GitHub: https://github.com/r9y9/tacotron_pytorch
Oct 15, 2017 7 min read
GAN 日本語音声合成 [arXiv:1709.08041]
IEEE TASLP: https://ieeexplore.ieee.org/document/8063435/
Oct 10, 2017 3 min read
【音声合成編】Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks [arXiv:1709.08041]
IEEE TASLP: https://ieeexplore.ieee.org/document/8063435/
Oct 9, 2017 4 min read
【声質変換編】Statistical Parametric Speech Synthesis Incorporating Generative Adversarial Networks [arXiv:1709.08041]
IEEE TASLP: https://ieeexplore.ieee.org/document/8063435/
Oct 5, 2017 3 min read
DNN音声合成のためのライブラリの紹介とDNN日本語音声合成の実装例
GitHub: https://github.com/r9y9/nnmnkwii
Aug 16, 2017 2 min read
DNN統計的音声合成ツールキット Merlin の中身を理解をする
GitHub: https://cstr-edinburgh.github.io/merlin/
Aug 16, 2017 2 min read
PythonによるニューラルネットのToyコード
https://github.com/r9y9/python-neural-net-toy-codes
May 11, 2014 3 min read