Picture for Hirokazu Kameoka

Hirokazu Kameoka

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

Add code
Mar 25, 2024
Figure 1 for Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
Figure 2 for Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
Figure 3 for Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
Figure 4 for Training Generative Adversarial Network-Based Vocoder with Limited Data Using Augmentation-Conditional Discriminator
Viaarxiv icon

iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN

Add code
Aug 14, 2023
Figure 1 for iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Figure 2 for iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Figure 3 for iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Figure 4 for iSTFTNet2: Faster and More Lightweight iSTFT-Based Neural Vocoder Using 1D-2D CNN
Viaarxiv icon

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

Add code
Mar 24, 2023
Figure 1 for Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Figure 2 for Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Figure 3 for Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Figure 4 for Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
Viaarxiv icon

Speak Like a Dog: Human to Non-human creature Voice Conversion

Add code
Jun 09, 2022
Figure 1 for Speak Like a Dog: Human to Non-human creature Voice Conversion
Figure 2 for Speak Like a Dog: Human to Non-human creature Voice Conversion
Figure 3 for Speak Like a Dog: Human to Non-human creature Voice Conversion
Figure 4 for Speak Like a Dog: Human to Non-human creature Voice Conversion
Viaarxiv icon

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

Add code
Mar 04, 2022
Figure 1 for iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Figure 2 for iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Figure 3 for iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Figure 4 for iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Viaarxiv icon

FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures

Add code
Sep 28, 2021
Figure 1 for FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures
Figure 2 for FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures
Figure 3 for FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures
Figure 4 for FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures
Viaarxiv icon

StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition

Add code
Aug 10, 2021
Figure 1 for StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
Figure 2 for StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
Figure 3 for StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
Figure 4 for StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition
Viaarxiv icon

FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion

Add code
Apr 14, 2021
Figure 1 for FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
Figure 2 for FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
Figure 3 for FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
Figure 4 for FastS2S-VC: Streaming Non-Autoregressive Sequence-to-Sequence Voice Conversion
Viaarxiv icon

StarGAN-based Emotional Voice Conversion for Japanese Phrases

Add code
Apr 05, 2021
Figure 1 for StarGAN-based Emotional Voice Conversion for Japanese Phrases
Figure 2 for StarGAN-based Emotional Voice Conversion for Japanese Phrases
Figure 3 for StarGAN-based Emotional Voice Conversion for Japanese Phrases
Figure 4 for StarGAN-based Emotional Voice Conversion for Japanese Phrases
Viaarxiv icon

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

Add code
Feb 25, 2021
Figure 1 for MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
Figure 2 for MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
Figure 3 for MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
Figure 4 for MaskCycleGAN-VC: Learning Non-parallel Voice Conversion with Filling in Frames
Viaarxiv icon