Hirokazu Kameoka | SigPort

Primary tabs

Author's Documents

Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator

13 April 2024 - 11:17am 58 Downloads

Takuhiro Kaneko

,

Hirokazu Kameoka

,

Read More

Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis

1 June 2023 - 1:37am 143 Downloads

Takuhiro Kaneko

,

Hirokazu Kameoka

,

Read More

iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform

12 May 2022 - 3:26am 187 Downloads

Takuhiro Kaneko

,

,

Hirokazu Kameoka

Read More

MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames

29 June 2021 - 7:12am 191 Downloads

Takuhiro Kaneko

,

Hirokazu Kameoka

,

Read More

AttS2S-VC: Sequence-to-Sequence Voice Conversion with Attention and Context Preservation Mechanisms

15 May 2019 - 6:58am 617 Downloads

,

Hirokazu Kameoka

,

Takuhiro Kaneko

Read More

CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion

10 May 2019 - 2:49am 390 Downloads

Takuhiro Kaneko

,

Hirokazu Kameoka

Read More

Joint Separation and Dereverberation of Reverberant Mixtures with Determined Multichannel Non-negative Matrix Factorization

23 April 2018 - 4:58pm 437 Downloads

Hirokazu Kameoka

Read More