Alert button
Picture for Tomohiko Nakamura

Tomohiko Nakamura

Alert button

Real-time Speech Extraction Using Spatially Regularized Independent Low-rank Matrix Analysis and Rank-constrained Spatial Covariance Matrix Estimation

Add code
Bookmark button
Alert button
Mar 19, 2024
Yuto Ishikawa, Kohei Konaka, Tomohiko Nakamura, Norihiro Takamune, Hiroshi Saruwatari

Figure 1 for Real-time Speech Extraction Using Spatially Regularized Independent Low-rank Matrix Analysis and Rank-constrained Spatial Covariance Matrix Estimation
Figure 2 for Real-time Speech Extraction Using Spatially Regularized Independent Low-rank Matrix Analysis and Rank-constrained Spatial Covariance Matrix Estimation
Figure 3 for Real-time Speech Extraction Using Spatially Regularized Independent Low-rank Matrix Analysis and Rank-constrained Spatial Covariance Matrix Estimation
Viaarxiv icon

Sampling-Frequency-Independent Universal Sound Separation

Add code
Bookmark button
Alert button
Sep 22, 2023
Tomohiko Nakamura, Kohei Yatabe

Viaarxiv icon

Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides

Add code
Bookmark button
Alert button
Jun 19, 2023
Kanami Imamura, Tomohiko Nakamura, Norihiro Takamune, Kohei Yatabe, Hiroshi Saruwatari

Figure 1 for Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides
Figure 2 for Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides
Figure 3 for Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides
Figure 4 for Algorithms of Sampling-Frequency-Independent Layers for Non-integer Strides
Viaarxiv icon

How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics

Add code
Bookmark button
Alert button
Jun 01, 2023
Joonyong Park, Shinnosuke Takamichi, Tomohiko Nakamura, Kentaro Seki, Detai Xin, Hiroshi Saruwatari

Figure 1 for How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics
Figure 2 for How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics
Figure 3 for How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics
Figure 4 for How Generative Spoken Language Modeling Encodes Noisy Speech: Investigation from Phonetics to Syntactics
Viaarxiv icon

jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus

Add code
Bookmark button
Alert button
Dec 09, 2022
Tomohiko Nakamura, Shinnosuke Takamichi, Naoko Tanji, Satoru Fukayama, Hiroshi Saruwatari

Figure 1 for jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
Figure 2 for jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
Figure 3 for jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
Figure 4 for jaCappella Corpus: A Japanese a Cappella Vocal Ensemble Corpus
Viaarxiv icon

Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders

Add code
Bookmark button
Alert button
Sep 27, 2022
Futa Nakashima, Tomohiko Nakamura, Norihiro Takamune, Satoru Fukayama, Hiroshi Saruwatari

Figure 1 for Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders
Figure 2 for Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders
Figure 3 for Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders
Figure 4 for Hyperbolic Timbre Embedding for Musical Instrument Sound Synthesis Based on Variational Autoencoders
Viaarxiv icon

Head-Related Transfer Function Interpolation from Spatially Sparse Measurements Using Autoencoder with Source Position Conditioning

Add code
Bookmark button
Alert button
Jul 22, 2022
Yuki Ito, Tomohiko Nakamura, Shoichi Koyama, Hiroshi Saruwatari

Figure 1 for Head-Related Transfer Function Interpolation from Spatially Sparse Measurements Using Autoencoder with Source Position Conditioning
Figure 2 for Head-Related Transfer Function Interpolation from Spatially Sparse Measurements Using Autoencoder with Source Position Conditioning
Figure 3 for Head-Related Transfer Function Interpolation from Spatially Sparse Measurements Using Autoencoder with Source Position Conditioning
Viaarxiv icon

Physics-informed convolutional neural network with bicubic spline interpolation for sound field estimation

Add code
Bookmark button
Alert button
Jul 22, 2022
Kazuhide Shigemi, Shoichi Koyama, Tomohiko Nakamura, Hiroshi Saruwatari

Figure 1 for Physics-informed convolutional neural network with bicubic spline interpolation for sound field estimation
Figure 2 for Physics-informed convolutional neural network with bicubic spline interpolation for sound field estimation
Figure 3 for Physics-informed convolutional neural network with bicubic spline interpolation for sound field estimation
Viaarxiv icon

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

Add code
Bookmark button
Alert button
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

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

Add code
Bookmark button
Alert button
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