Many-to-Many Voice Transformer Network

May 18, 2020
Hirokazu Kameoka, Wen-Chin Huang, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Tomoki Toda


  Access Model/Code and Paper
Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining

Dec 14, 2019
Wen-Chin Huang, Tomoki Hayashi, Yi-Chiao Wu, Hirokazu Kameoka, Tomoki Toda

* Preprint. Work in progress 

  Access Model/Code and Paper
StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion

Aug 07, 2019
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo

* Accepted to Interspeech 2019. Project page: http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/stargan-vc2/index.html 

  Access Model/Code and Paper
CycleGAN-VC2: Improved CycleGAN-based Non-parallel Voice Conversion

Apr 09, 2019
Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo

* Accepted to ICASSP 2019. Project page: http://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/cyclegan-vc2/index.html 

  Access Model/Code and Paper
Crossmodal Voice Conversion

Apr 09, 2019
Hirokazu Kameoka, Kou Tanaka, Aaron Valero Puche, Yasunori Ohishi, Takuhiro Kaneko

* Submitted to Interspeech2019 

  Access Model/Code and Paper
WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation

Apr 09, 2019
Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo

* Submitted to INTERSPEECH2019 

  Access Model/Code and Paper
Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform

Apr 07, 2019
Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi

* Submitted to Interspeech 2019, Graz, Austria 

  Access Model/Code and Paper
Fast MVAE: Joint separation and classification of mixed sources based on multichannel variational autoencoder with auxiliary classifier

Dec 16, 2018
Li Li, Hirokazu Kameoka, Shoji Makino

* Submitted to ICASSP 2019 

  Access Model/Code and Paper
AttS2S-VC: Sequence-to-Sequence Voice Conversion with Attention and Context Preservation Mechanisms

Nov 09, 2018
Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo

* Submitted to ICASSP2019 

  Access Model/Code and Paper
ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion

Nov 05, 2018
Hirokazu Kameoka, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo


  Access Model/Code and Paper
Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation

Sep 29, 2018
Shogo Seki, Hirokazu Kameoka, Li Li, Tomoki Toda, Kazuya Takeda


  Access Model/Code and Paper
WaveCycleGAN: Synthetic-to-natural speech waveform conversion using cycle-consistent adversarial networks

Sep 28, 2018
Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Hirokazu Kameoka

* SLT2018 

  Access Model/Code and Paper
ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder

Aug 26, 2018
Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo

* arXiv admin note: substantial text overlap with arXiv:1806.02169. arXiv admin note: substantial text overlap with arXiv:1806.02169 

  Access Model/Code and Paper
Semi-blind source separation with multichannel variational autoencoder

Aug 26, 2018
Hirokazu Kameoka, Li Li, Shota Inoue, Shoji Makino


  Access Model/Code and Paper
StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks

Jun 29, 2018
Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo


  Access Model/Code and Paper
Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms

Apr 06, 2018
Keisuke Oyamada, Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo, Hiroyasu Ando


  Access Model/Code and Paper
Speech waveform synthesis from MFCC sequences with generative adversarial networks

Apr 03, 2018
Lauri Juvela, Bajibabu Bollepalli, Xin Wang, Hirokazu Kameoka, Manu Airaksinen, Junichi Yamagishi, Paavo Alku


  Access Model/Code and Paper
Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks

Dec 20, 2017
Takuhiro Kaneko, Hirokazu Kameoka


  Access Model/Code and Paper
Designing various component analysis at will

Oct 05, 2012
Akisato Kimura, Masashi Sugiyama, Sakano Hitoshi, Hirokazu Kameoka

* Accepted to IAPR International Conference on Pattern Recognition, submitted to IPSJ Transactions on Mathematical Modeling and its Applications (TOM). Just only one-page abstract for new due to novelty violation for journal submission. The details will be disclosed in late September 

  Access Model/Code and Paper