Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Kazuyoshi Yoshii

Kazuyoshi Yoshii

Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms


May 12, 2021
Ryoto Ishizuka, Ryo Nishikimi, Kazuyoshi Yoshii

Figure 1 for Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms
Figure 2 for Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms
Figure 3 for Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms
Figure 4 for Global Structure-Aware Drum Transcription Based on Self-Attention Mechanisms
* Submitted to Signals (ISSN 2624-6120) 
  Access Paper or Ask Questions

Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training


Oct 08, 2020
Ryoto Ishizuka, Ryo Nishikimi, Eita Nakamura, Kazuyoshi Yoshii

Figure 1 for Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training
Figure 2 for Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training
Figure 3 for Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training
Figure 4 for Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training
* Accepted to APSIPA 2020 
  Access Paper or Ask Questions

The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction


Sep 30, 2020
Andrew McLeod, James Owers, Kazuyoshi Yoshii

Figure 1 for The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction
Figure 2 for The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction
Figure 3 for The MIDI Degradation Toolkit: Symbolic Music Augmentation and Correction
* Authors 1 and 2 contributed equally to this work. Accepted by International Society for Music Information Retrieval Conference (ISMIR), 2020 
  Access Paper or Ask Questions

Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords


May 14, 2020
Yiming Wu, Tristan Carsault, Eita Nakamura, Kazuyoshi Yoshii

Figure 1 for Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords
Figure 2 for Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords
Figure 3 for Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords
Figure 4 for Semi-supervised Neural Chord Estimation Based on a Variational Autoencoder with Discrete Labels and Continuous Textures of Chords

  Access Paper or Ask Questions

MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images


Apr 08, 2020
Takayuki Nakatsuka, Kazuyoshi Yoshii, Yuki Koyama, Satoru Fukayama, Masataka Goto, Shigeo Morishima

Figure 1 for MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
Figure 2 for MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
Figure 3 for MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
Figure 4 for MirrorNet: A Deep Bayesian Approach to Reflective 2D Pose Estimation from Human Images
* 19 pages 
  Access Paper or Ask Questions

Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network


Nov 12, 2019
Tristan Carsault, Andrew McLeod, Philippe Esling, Jérôme Nika, Eita Nakamura, Kazuyoshi Yoshii

Figure 1 for Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
Figure 2 for Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
Figure 3 for Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
Figure 4 for Multi-Step Chord Sequence Prediction Based on Aggregated Multi-Scale Encoder-Decoder Network
* Accepted for publication in MLSP, 2019 
  Access Paper or Ask Questions

Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model


Aug 29, 2019
Yoshiaki Bando, Yoko Sasaki, Kazuyoshi Yoshii

Figure 1 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
Figure 2 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
Figure 3 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
Figure 4 for Deep Bayesian Unsupervised Source Separation Based on a Complex Gaussian Mixture Model
* 6 pages, 2 figures, accepted for publication in 2019 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 
  Access Paper or Ask Questions

Music Transcription Based on Bayesian Piece-Specific Score Models Capturing Repetitions


Aug 18, 2019
Eita Nakamura, Kazuyoshi Yoshii

Figure 1 for Music Transcription Based on Bayesian Piece-Specific Score Models Capturing Repetitions
Figure 2 for Music Transcription Based on Bayesian Piece-Specific Score Models Capturing Repetitions
Figure 3 for Music Transcription Based on Bayesian Piece-Specific Score Models Capturing Repetitions
Figure 4 for Music Transcription Based on Bayesian Piece-Specific Score Models Capturing Repetitions
* 17 pages, 9 figures, version submitted to IEEE/ACM TASLP 
  Access Paper or Ask Questions

Statistical Learning and Estimation of Piano Fingering


Apr 23, 2019
Eita Nakamura, Yasuyuki Saito, Kazuyoshi Yoshii

Figure 1 for Statistical Learning and Estimation of Piano Fingering
Figure 2 for Statistical Learning and Estimation of Piano Fingering
Figure 3 for Statistical Learning and Estimation of Piano Fingering
Figure 4 for Statistical Learning and Estimation of Piano Fingering
* 13 pages, 7 figures 
  Access Paper or Ask Questions

Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition


Mar 31, 2019
Kazuki Shimada, Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara

Figure 1 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition
Figure 2 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition
Figure 3 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition
Figure 4 for Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition

  Access Paper or Ask Questions

A Deep Generative Model of Speech Complex Spectrograms


Mar 08, 2019
Aditya Arie Nugraha, Kouhei Sekiguchi, Kazuyoshi Yoshii

Figure 1 for A Deep Generative Model of Speech Complex Spectrograms
Figure 2 for A Deep Generative Model of Speech Complex Spectrograms
Figure 3 for A Deep Generative Model of Speech Complex Spectrograms
Figure 4 for A Deep Generative Model of Speech Complex Spectrograms

  Access Paper or Ask Questions

Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices


Mar 08, 2019
Kouhei Sekiguchi, Aditya Arie Nugraha, Yoshiaki Bando, Kazuyoshi Yoshii

Figure 1 for Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices
Figure 2 for Fast Multichannel Source Separation Based on Jointly Diagonalizable Spatial Covariance Matrices

  Access Paper or Ask Questions

Statistical Piano Reduction Controlling Performance Difficulty


Oct 25, 2018
Eita Nakamura, Kazuyoshi Yoshii

Figure 1 for Statistical Piano Reduction Controlling Performance Difficulty
Figure 2 for Statistical Piano Reduction Controlling Performance Difficulty
Figure 3 for Statistical Piano Reduction Controlling Performance Difficulty
Figure 4 for Statistical Piano Reduction Controlling Performance Difficulty
* 12 pages, 7 figures, version accepted to APSIPA Transactions on Signal and Information Processing 
  Access Paper or Ask Questions

Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization


Mar 19, 2018
Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara

Figure 1 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
Figure 2 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
Figure 3 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
Figure 4 for Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
* 5 pages, 3 figures, version that Eqs. (9), (19), and (20) in v2 (submitted to ICASSP 2018) are corrected. Samples available here: http://sap.ist.i.kyoto-u.ac.jp/members/yoshiaki/demo/vae-nmf/ 
  Access Paper or Ask Questions

Generative Statistical Models with Self-Emergent Grammar of Chord Sequences


Mar 02, 2018
Hiroaki Tsushima, Eita Nakamura, Katsutoshi Itoyama, Kazuyoshi Yoshii

Figure 1 for Generative Statistical Models with Self-Emergent Grammar of Chord Sequences
Figure 2 for Generative Statistical Models with Self-Emergent Grammar of Chord Sequences
Figure 3 for Generative Statistical Models with Self-Emergent Grammar of Chord Sequences
Figure 4 for Generative Statistical Models with Self-Emergent Grammar of Chord Sequences
* 22 pages, 14 figures, version accepted to JNMR, minor revision 
  Access Paper or Ask Questions

Note Value Recognition for Piano Transcription Using Markov Random Fields


Jul 07, 2017
Eita Nakamura, Kazuyoshi Yoshii, Simon Dixon

Figure 1 for Note Value Recognition for Piano Transcription Using Markov Random Fields
Figure 2 for Note Value Recognition for Piano Transcription Using Markov Random Fields
Figure 3 for Note Value Recognition for Piano Transcription Using Markov Random Fields
Figure 4 for Note Value Recognition for Piano Transcription Using Markov Random Fields
* 13 pages, 16 figures, version accepted to IEEE/ACM TASLP, minor revision 
  Access Paper or Ask Questions

Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices


Jan 29, 2017
Eita Nakamura, Kazuyoshi Yoshii, Shigeki Sagayama

Figure 1 for Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices
Figure 2 for Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices
Figure 3 for Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices
Figure 4 for Rhythm Transcription of Polyphonic Piano Music Based on Merged-Output HMM for Multiple Voices
* 13 pages, 13 figures, version accepted to IEEE/ACM TASLP 
  Access Paper or Ask Questions