Picture for Kei Hashimoto

Kei Hashimoto

PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model

Add code
Feb 22, 2024
Viaarxiv icon

Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation

Add code
Jan 05, 2023
Viaarxiv icon

Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism

Add code
Dec 28, 2022
Viaarxiv icon

Embedding a Differentiable Mel-cepstral Synthesis Filter to a Neural Speech Synthesis System

Add code
Nov 21, 2022
Viaarxiv icon

Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism

Add code
Aug 31, 2021
Figure 1 for Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism
Figure 2 for Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism
Figure 3 for Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism
Viaarxiv icon

Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System

Add code
Aug 05, 2021
Figure 1 for Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System
Figure 2 for Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System
Figure 3 for Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System
Figure 4 for Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System
Viaarxiv icon

PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components

Add code
Feb 15, 2021
Figure 1 for PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
Figure 2 for PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
Figure 3 for PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
Figure 4 for PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
Viaarxiv icon

Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis

Add code
Sep 17, 2020
Figure 1 for Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
Figure 2 for Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
Figure 3 for Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
Figure 4 for Hierarchical Multi-Grained Generative Model for Expressive Speech Synthesis
Viaarxiv icon

Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks

Add code
Oct 24, 2019
Figure 1 for Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks
Figure 2 for Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks
Figure 3 for Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks
Figure 4 for Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks
Viaarxiv icon

Singing voice synthesis based on convolutional neural networks

Add code
Apr 15, 2019
Figure 1 for Singing voice synthesis based on convolutional neural networks
Figure 2 for Singing voice synthesis based on convolutional neural networks
Figure 3 for Singing voice synthesis based on convolutional neural networks
Figure 4 for Singing voice synthesis based on convolutional neural networks
Viaarxiv icon