Alert button
Picture for Hiroshi Saruwatari

Hiroshi Saruwatari

Alert button

Region-to-region kernel interpolation of acoustic transfer function with directional weighting

May 05, 2022
Juliano G. C. Ribeiro, Shoichi Koyama, Hiroshi Saruwatari

Figure 1 for Region-to-region kernel interpolation of acoustic transfer function with directional weighting
Figure 2 for Region-to-region kernel interpolation of acoustic transfer function with directional weighting
Figure 3 for Region-to-region kernel interpolation of acoustic transfer function with directional weighting
Figure 4 for Region-to-region kernel interpolation of acoustic transfer function with directional weighting
Viaarxiv icon

Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation

Apr 22, 2022
Detai Xin, Shinnosuke Takamichi, Takuma Okamoto, Hisashi Kawai, Hiroshi Saruwatari

Figure 1 for Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation
Figure 2 for Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation
Figure 3 for Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation
Figure 4 for Speaking-Rate-Controllable HiFi-GAN Using Feature Interpolation
Viaarxiv icon

UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022

Apr 05, 2022
Takaaki Saeki, Detai Xin, Wataru Nakata, Tomoki Koriyama, Shinnosuke Takamichi, Hiroshi Saruwatari

Figure 1 for UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
Figure 2 for UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
Figure 3 for UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
Figure 4 for UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022
Viaarxiv icon

STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent

Mar 28, 2022
Yuki Saito, Yuto Nishimura, Shinnosuke Takamichi, Kentaro Tachibana, Hiroshi Saruwatari

Figure 1 for STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
Figure 2 for STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
Figure 3 for STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
Figure 4 for STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
Viaarxiv icon

SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling

Mar 24, 2022
Takaaki Saeki, Shinnosuke Takamichi, Tomohiko Nakamura, Naoko Tanji, Hiroshi Saruwatari

Figure 1 for SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling
Figure 2 for SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling
Figure 3 for SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling
Figure 4 for SelfRemaster: Self-Supervised Speech Restoration with Analysis-by-Synthesis Approach Using Channel Modeling
Viaarxiv icon

Personalized filled-pause generation with group-wise prediction models

Mar 18, 2022
Yuta Matsunaga, Takaaki Saeki, Shinnosuke Takamichi, Hiroshi Saruwatari

Figure 1 for Personalized filled-pause generation with group-wise prediction models
Figure 2 for Personalized filled-pause generation with group-wise prediction models
Figure 3 for Personalized filled-pause generation with group-wise prediction models
Figure 4 for Personalized filled-pause generation with group-wise prediction models
Viaarxiv icon

Spatial active noise control based on individual kernel interpolation of primary and secondary sound fields

Feb 10, 2022
Kazuyuki Arikawa, Shoichi Koyama, Hiroshi Saruwatari

Figure 1 for Spatial active noise control based on individual kernel interpolation of primary and secondary sound fields
Figure 2 for Spatial active noise control based on individual kernel interpolation of primary and secondary sound fields
Figure 3 for Spatial active noise control based on individual kernel interpolation of primary and secondary sound fields
Figure 4 for Spatial active noise control based on individual kernel interpolation of primary and secondary sound fields
Viaarxiv icon

Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds

Feb 01, 2022
Masaya Kawamura, Tomohiko Nakamura, Daichi Kitamura, Hiroshi Saruwatari, Yu Takahashi, Kazunobu Kondo

Figure 1 for Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds
Figure 2 for Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds
Figure 3 for Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds
Viaarxiv icon

J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis

Jan 26, 2022
Shinnosuke Takamichi, Wataru Nakata, Naoko Tanji, Hiroshi Saruwatari

Figure 1 for J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Figure 2 for J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Figure 3 for J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Figure 4 for J-MAC: Japanese multi-speaker audiobook corpus for speech synthesis
Viaarxiv icon

Mean-square-error-based secondary source placement in sound field synthesis with prior information on desired field

Dec 10, 2021
Keisuke Kimura, Shoichi Koyama, Natsuki Ueno, Hiroshi Saruwatari

Figure 1 for Mean-square-error-based secondary source placement in sound field synthesis with prior information on desired field
Figure 2 for Mean-square-error-based secondary source placement in sound field synthesis with prior information on desired field
Figure 3 for Mean-square-error-based secondary source placement in sound field synthesis with prior information on desired field
Figure 4 for Mean-square-error-based secondary source placement in sound field synthesis with prior information on desired field
Viaarxiv icon