Hirokazu Kameoka

发表

Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks pdf

Hirokazu Kameoka, Takuhiro Kaneko, H. Kameoka, 2017, ArXiv.

Fast MVAE: Joint Separation and Classification of Mixed Sources Based on Multichannel Variational Autoencoder with Auxiliary Classifier

Li Li, Hirokazu Kameoka, Shoji Makino, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Music Factorizer: A note-by-note editing interface for music waveforms

Hirokazu Kameoka, Kunio Kashino, Jonathan Le Roux, 2009 .

Probabilistic model of two-dimensional rhythm tree structure representation for automatic transcription of polyphonic MIDI signals

Hirokazu Kameoka, Shigeki Sagayama, Masato Tsuchiya, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

Maximum reconstruction probability training of Restricted Boltzmann machines with auxiliary function approach

Hirokazu Kameoka, Norihiro Takamune, 2014, 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

Statistical modeling of F0 dynamics in singing voices based on Gaussian processes with multiple oscillation bases

Hirokazu Kameoka, Kunio Kashino, Daichi Mochihashi, 2010, INTERSPEECH.

Specmurt Analysis of Polyphonic Music Signals

Hirokazu Kameoka, Keigo Takahashi, Shigeki Sagayama, 2008, IEEE Transactions on Audio, Speech, and Language Processing.

Semi-Supervised Joint Enhancement of Spectral and Cepstral Sequences of Noisy Speech

Li Li, Hirokazu Kameoka, Takuya Higuchi, 2016, INTERSPEECH.

Transition Pattern Extraction Based on Location History Considering Missing Value and Periodicity

Hirokazu Kameoka, Hiroshi Sawada, Aki Hayashi, 2017 .

Modulation analysis of speech through orthogonal FIR filterbank optimization

Hirokazu Kameoka, Jonathan Le Roux, Alain de Cheveigné, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Divergence optimization in nonnegative matrix factorization with spectrogram restoration for multichannel signal separation

Hirokazu Kameoka, Satoshi Nakamura, Hiroshi Saruwatari, 2014, 2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA).

Sequence-to-Sequence Voice Conversion with Similarity Metric Learned Using Generative Adversarial Networks

Hirokazu Kameoka, Kunio Kashino, Takuhiro Kaneko, 2017, INTERSPEECH.

Selective Amplifier of Periodic and Non-periodic Components in Concurrent Audio Signals with Spectral Control Envelopes

Hirokazu Kameoka, Masataka Goto, Shigeki Sagayama, 2006 .

Many-to-Many Voice Transformer Network

Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Reverberation-robust underdetermined source separation with non-negative tensor double deconvolution

Hirokazu Kameoka, Tomohiro Nakatani, Shoko Araki, 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

Efficient algorithms for multichannel extensions of Itakura-Saito nonnegative matrix factorization

Hirokazu Kameoka, Naonori Ueda, Hiroshi Sawada, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2020, INTERSPEECH.

Unified approach for underdetermined BSS, VAD, dereverberation and DOA estimation with multichannel factorial HMM

Hirokazu Kameoka, Takuya Higuchi, 2014, 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

Separation of harmonic structures based on tied Gaussian mixture model and information criterion for concurrent sounds

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Computational auditory induction as a missing-data model-fitting problem with Bregman divergence

Hirokazu Kameoka, Jonathan Le Roux, Alain de Cheveigné, 2011, Speech Commun..

Efficient multichannel nonnegative matrix factorization exploiting rank-1 spatial model

Hirokazu Kameoka, Hiroshi Sawada, Hiroshi Saruwatari, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Constrained and regularized variants of non-negative matrix factorization incorporating music-specific constraints

Hirokazu Kameoka, Kunio Kashino, Masahiro Nakano, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining pdf

Hirokazu Kameoka, Tomoki Toda, Yi-Chiao Wu, 2019, INTERSPEECH.

Underdetermined blind separation and tracking of moving sources based ONDOA-HMM

Hirokazu Kameoka, Takuya Higuchi, Norihiro Takamune, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Generative adversarial network-based approach to signal reconstruction from magnitude spectrogram

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

Determined Audio Source Separation with Multichannel Star Generative Adversarial Network

Hirokazu Kameoka, Li Li, Shoji Makino, 2020, 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP).

Apparatus, method, and program for signal separation

Hirokazu Kameoka, Shigeki Sagayama, Emmanuel Vincent, 2010 .

A noise suppression method for body-conducted soft speech based on non-negative tensor factorization of air- and body-conducted signals

Hirokazu Kameoka, Tomoki Toda, Yusuke Tajiri, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Underdetermined Source Separation Based on Generalized Multichannel Variational Autoencoder

Hirokazu Kameoka, Li Li, Kazuya Takeda, 2019, IEEE Access.

Text-to-speech synthesizer based on combination of composite wavelet and hidden Markov models

Hirokazu Kameoka, Daisuke Saito, Shigeki Sagayama, 2013, SSW.

Speech Enhancement Using Non-Negative Spectrogram Models with Mel-Generalized Cepstral Regularization

Li Li, Hirokazu Kameoka, Tomoki Toda, 2017, INTERSPEECH.

Consistent Wiener Filtering: Generalized Time-Frequency Masking Respecting Spectrogram Consistency

Hirokazu Kameoka, Jonathan Le Roux, Emmanuel Vincent, 2010, LVA/ICA.

Generative Adversarial Network-Based Postfilter for STFT Spectrograms

Hirokazu Kameoka, Takuhiro Kaneko, Junichi Yamagishi, 2017, INTERSPEECH.

Nonnegative Matrix Factorization with Markov-Chained Bases for Modeling Time-Varying Patterns in Music Spectrograms

Hirokazu Kameoka, Jonathan Le Roux, Masahiro Nakano, 2010, LVA/ICA.

Modeling speech parameter sequences with latent trajectory Hidden Markov model

Hirokazu Kameoka, H. Kameoka, 2015, 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP).

Hidden Markov Convolutive Mixture Model for Pitch Contour Analysis of Speech

Hirokazu Kameoka, Daisuke Saito, Shigeki Sagayama, 2012, INTERSPEECH.

Relaxation of rank-1 spatial constraint in overdetermined blind source separation

Hirokazu Kameoka, Hiroshi Sawada, Hiroshi Saruwatari, 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

Direct linear conversion of LSP parameters for perceptual control in speech and audio coding

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

Automatic audio tag classification via semi-supervised canonical density estimation

Hirokazu Kameoka, Masashi Sugiyama, Makoto Yamada, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Independent Low-Rank Matrix Analysis Based on Generalized Kullback-Leibler Divergence

Hirokazu Kameoka, Hiroshi Saruwatari, Hiroaki Nakajima, 2019, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

Harmonic-Temporal Clustering via Deterministic Annealing EM Algorithm for Audio Feature Extraction

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2005, ISMIR.

Acoustic-to-Articulatory Inversion Mapping Based on Latent Trajectory Gaussian Mixture Model

Hirokazu Kameoka, Tomoki Toda, Satoshi Nakamura, 2016, INTERSPEECH.

Input-Output HMM Applied to Automatic Arrangement for Guitars

Hirokazu Kameoka, Shigeki Sagayama, Gen Hori, 2013, J. Inf. Process..

Automatic Decision of Piano Fingering Based on a Hidden Markov Models

Hirokazu Kameoka, Shigeki Sagayama, Yuichiro Yonebayashi, 2007, IJCAI.

Statistical Model of Speech Signals Based on Composite Autoregressive System with Application to Blind Source Separation

Hirokazu Kameoka, Kunio Kashino, Jonathan Le Roux, 2010, LVA/ICA.

Self-localization and channel synchronization of smartphone arrays using sound emissions

Hirokazu Kameoka, Nobutaka Ono, Kazuaki Shibata, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Speech prosody generation for text-to-speech synthesis based on generative model of F0 contours

Hirokazu Kameoka, Nobukatsu Hojo, Kento Kadowaki, 2014, INTERSPEECH.

A Linear Predictive Coding Algorithm Minimizing the Golomb-Rice Code Length of the Residual Signal

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2008 .

New formulations and efficient algorithms for multichannel NMF

Hirokazu Kameoka, Naonori Ueda, Hiroshi Sawada, 2011, 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Harmonic-Temporal-Timbral Clustering (HTTC) for the analysis of multi-instrument polyphonic music signals

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Designing various component analysis at will

Hirokazu Kameoka, Masashi Sugiyama, Hitoshi Sakano, 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

An Investigation of Features for Fundamental Frequency Pattern Prediction in Electrolaryngeal Speech Enhancement

Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, 2019, 10th ISCA Workshop on Speech Synthesis (SSW 10).

VoiceGrad: Non-Parallel Any-to-Many Voice Conversion With Annealed Langevin Dynamics pdf

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Timbre replacement of harmonic and drum components for music audio signals

Hirokazu Kameoka, Masataka Goto, Kazuyoshi Yoshii, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-pitch Detection Algorithm Using Constrained Gaussian Mixture Model and Information Criterion for Simultaneous Speech

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2004 .

Switching acausal filters for speech modeling

Hirokazu Kameoka, Yasuhiro Minami, H. Kameoka, 2009, 2009 IEEE International Workshop on Machine Learning for Signal Processing.

Semantic Indexing and Known Item Search Based on a Unified Model with Topic Transition Representation

Hirokazu Kameoka, Kunio Kashino, Shigeki Sagayama, 2010, TRECVID.

Blind Separation of Infinitely Many Sparse Sources

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2012, IWAENC.

Polyphonic music signal analysis using non-negative matrix factorization with deformable bases

Hirokazu Kameoka, Jonathan Le Roux, Masahiro Nakano, 2010 .

Text-to-speech prosody synthesis based on probabilistic model for F_0 contour : The Technical Report

Hirokazu Kameoka, Nobukatsu Hojo, Kento Kadowaki, 2014 .

Single and Multiple F0 Contour Estimation Through Parametric Spectrogram Modeling of Speech in Noisy Environments

Hirokazu Kameoka, Jonathan Le Roux, Alain de Cheveigné, 2007, IEEE Trans. Speech Audio Process..

A statistical model of speech F0 contours

Hirokazu Kameoka, Jonathan Le Roux, Yasunori Ohishi, 2010, SAPA@INTERSPEECH.

Formulations and algorithms for multichannel complex NMF

Hirokazu Kameoka, Naonori Ueda, Hiroshi Sawada, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Nonnegative Matrix Factorization With Basis Clustering Using Cepstral Distance Regularization

Hirokazu Kameoka, Takuya Higuchi, Mikihiro Tanaka, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Complex NMF with the generalized Kullback-Leibler divergence

Hirokazu Kameoka, Masahiro Yukawa, Hideaki Kagami, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Separation of a monaural audio signal into harmonic/percussive components by complementary diffusion on spectrogram

Hirokazu Kameoka, Jonathan Le Roux, Shigeki Sagayama, 2008, 2008 16th European Signal Processing Conference.

Generative adversarial network-based approach to signal reconstruction from magnitude spectrograms

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018 .

Speech analyzer using a joint estimation model of spectral envelope and fine structure

Hirokazu Kameoka, Jonathan Le Roux, Shigeki Sagayama, 2006, INTERSPEECH.

Crossmodal Voice Conversion pdf

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2019, ArXiv.

Unified approach for audio source separation with multichannel factorial HMM and DOA mixture model

Hirokazu Kameoka, Takuya Higuchi, H. Kameoka, 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

Vae-Space: Deep Generative Model of Voice Fundamental Frequency Contours

Kou Tanaka, Hirokazu Kameoka, Kazuho Morikawa, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech Waveform Synthesis from MFCC Sequences with Generative Adversarial Networks

Bajibabu Bollepalli, Lauri Juvela, Paavo Alku, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Golomb-rice coding optimized via LPC for frequency domain audio coder

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2014, 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

A Real-time Equalizer of Harmonic and Percussive Components in Music Signals

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2008, ISMIR.

Generative Modeling of Voice Fundamental Frequency Contours

Hirokazu Kameoka, Kunio Kashino, Yasunori Ohishi, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Generative adversarial network-based postfilter for statistical parametric speech synthesis

Hirokazu Kameoka, Kunio Kashino, Takuhiro Kaneko, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Semi-blind source separation with multichannel variational autoencoder pdf

Li Li, Hirokazu Kameoka, Shoji Makino, 2018, ArXiv.

Specmurt Analysis of Multi-Pitch Music Signals with Adaptive Estimation of Common Harmonic Structure

Hirokazu Kameoka, Shigeki Sagayama, Shoichiro Saito, 2005, ISMIR.

SemiCCA: Efficient Semi-supervised Learning of Canonical Correlations

Hirokazu Kameoka, Masashi Sugiyama, Hitoshi Sakano, 2010, 2010 20th International Conference on Pattern Recognition.

A sparse component model of source signals and its application to blind source separation

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Comparative evaluations of various harmonic/percussive sound separation algorithms based on anisotropic continuity of spectrogram

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-negative Matrix Factorization and Its Variants with Applications to Audio Signal Processing( Multivariate Data Analysis with Matrix Factorization)

Hirokazu Kameoka, 2015 .

1. Music and Statistical Signal Processing

Hirokazu Kameoka, H. Kameoka, 2017 .

Harmonic-Temporal Clustering of Speech for Single and Multiple F0 Contour Estimation in Noisy Environments

Hirokazu Kameoka, Jonathan Le Roux, Alain de Cheveigné, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Harmonic-Temporal Factor Decomposition for Unsupervised Monaural Separation of Harmonic Sounds

Hirokazu Kameoka, Tomohiko Nakamura, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

WaveCycleGAN2: Time-domain Neural Post-filter for Speech Waveform Generation pdf

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2019, ArXiv.

Lp-norm non-negative matrix factorization and its application to singing voice enhancement

Hirokazu Kameoka, Tomohiko Nakamura, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cyclegan-VC2: Improved Cyclegan-based Non-parallel Voice Conversion

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-Parallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2020 .

A majorization-minimization algorithm with projected gradient updates for time-domain spectrogram factorization

Hirokazu Kameoka, Masahiro Yukawa, Hideaki Kagami, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Statistical models for speech dereverberation

Hirokazu Kameoka, Tomohiro Nakatani, Takuya Yoshioka, 2009, 2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

Infinite-state spectrum model for music signal analysis

Hirokazu Kameoka, Jonathan Le Roux, Masahiro Nakano, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ACVAE-VC: Non-parallel many-to-many voice conversion with auxiliary classifier variational autoencoder pdf

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, ArXiv.

Joint audio source separation and dereverberation based on multichannel factorial hidden Markov model

Hirokazu Kameoka, Takuya Higuchi, 2014, 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

HARMONIC-TEMPORAL CLUSTERINGOF SPEECHFOR SINGLEAND MULTIPLEFo CONTOUR ESTIMATIONINNOISYENVIRONMENTS

Hirokazu Kameoka, Nobutaka Ono, Jonathan LeRoux, 2007 .

Non-negative Matrix Factorization and Its Variants for Audio Signal Processing

Hirokazu Kameoka, 2016 .

A Stochastic Model of Singing Voice F0 Contours for Characterizing Expressive Dynamic Components

Hirokazu Kameoka, Kunio Kashino, Daichi Mochihashi, 2012, INTERSPEECH.

Complex NMF: A new sparse representation for acoustic signals

Hirokazu Kameoka, Kunio Kashino, Shigeki Sagayama, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Majorization-Minimization Algorithm for Discriminative Non-Negative Matrix Factorization

Hirokazu Kameoka, Li Li, Shoji Makino, 2020, IEEE Access.

Single Channel Speech and Background Segregation Through Harmonic-Temporal Clustering

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2007, 2007 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics.

StarGAN-VC: non-parallel many-to-many Voice Conversion Using Star Generative Adversarial Networks

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Ongaku Symposium 2014 : The 2nd Symposium on All Topics Related to Acoustics, Audition and Natural Language

Hirokazu Kameoka, Shoei Sato, Kazuyoshi Yoshii, 2014 .

Specmurt anasylis: a piano-roll-visualization of polyphonic music signal by deconvolution of log-frequency spectrum

Hirokazu Kameoka, Keigo Takahashi, Shigeki Sagayama, 2004, SAPA@INTERSPEECH.

Generalized Multichannel Variational Autoencoder for Underdetermined Source Separation

Li Li, Hirokazu Kameoka, Tomoki Toda, 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

Harmonic and Percussive Sound Separation and Its Application to MIR-Related Tasks

Hirokazu Kameoka, Jonathan Le Roux, Emiru Tsunoo, 2010, Advances in Music Information Retrieval.

ConvS2S-VC: Fully Convolutional Sequence-to-Sequence Voice Conversion

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Synthetic-to-Natural Speech Waveform Conversion Using Cycle-Consistent Adversarial Networks

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Joint Separation and Dereverberation of Reverberant Mixtures with Multichannel Variational Autoencoder

Hirokazu Kameoka, Shoji Makino, Li Li, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Majorisation-Minimisation Based Optimisation of the Composite Autoregressive System with Application to Glottal Inverse Filtering

Lauri Juvela, Paavo Alku, Hirokazu Kameoka, 2016, INTERSPEECH.

Nonparallel Voice Conversion With Augmented Classifier Star Generative Adversarial Networks

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Mixture of Gaussian process experts for predicting sung melodic contour with expressive dynamic fluctuations

Hirokazu Kameoka, Kunio Kashino, Daichi Mochihashi, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-native speech conversion with consistency-aware recursive network and generative adversarial network

Hirokazu Kameoka, Kunio Kashino, Takuhiro Kaneko, 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

A Multipitch Analyzer Based on Harmonic Temporal Structured Clustering

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2007, IEEE Transactions on Audio, Speech, and Language Processing.

Harmonic/Percussive Sound Separation Based on Anisotropic Smoothness of Spectrograms

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Sparse sound field decomposition with multichannel extension of complex NMF

Hirokazu Kameoka, Hiroshi Saruwatari, Shoichi Koyama, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

X-DC: Explainable Deep Clustering based on Learnable Spectrogram Templates

Hirokazu Kameoka, Chihiro Watanabe, 2020 .

Probabilistic speech F0 contour model incorporating statistical vocabulary model of phrase-accent command sequence

Hirokazu Kameoka, Daisuke Saito, Shigeki Sagayama, 2013, INTERSPEECH.

Multichannel Extensions of Non-Negative Matrix Factorization With Complex-Valued Data

Hirokazu Kameoka, Shoko Araki, Naonori Ueda, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

Robust speech dereverberation based on non-negativity and sparse nature of speech spectrograms

Hirokazu Kameoka, Tomohiro Nakatani, Takuya Yoshioka, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

A Modified Algorithm for Multiple Input Spectrogram Inversion

Hirokazu Kameoka, Dongxiao Wang, Koichi Shinoda, 2019, INTERSPEECH.

Fast Signal Reconstruction from Magnitude Spectrogram of Continuous Wavelet Transform Based on Spectrogram Consistency

Hirokazu Kameoka, Tomohiko Nakamura, 2014, DAFx.

Automatic video annotation via Hierarchical Topic Trajectory Model considering cross-modal correlations

Hirokazu Kameoka, Kunio Kashino, Shigeki Sagayama, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Computational auditory induction by missing-data non-negative matrix factorization

Hirokazu Kameoka, Jonathan Le Roux, Alain de Cheveigné, 2008, SAPA@INTERSPEECH.

StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2019, INTERSPEECH.

FastMVAE: A Fast Optimization Algorithm for the Multichannel Variational Autoencoder Method

Hirokazu Kameoka, Li Li, Shoji Makino, 2020, IEEE Access.

Bayesian nonparametric spectrogram modeling based on infinite factorial infinite hidden Markov model

Hirokazu Kameoka, Jonathan Le Roux, Masahiro Nakano, 2011, 2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).

Context-free 2D Tree Structure Model of Musical Notes for Bayesian Modeling of Polyphonic Spectrograms

Hirokazu Kameoka, Masahiro Nakano, Shigeki Sagayama, 2012, ISMIR.

A unified approach for underdetermined blind signal separation and source activity detection by multichannel factorial hidden Markov models

Hirokazu Kameoka, Takuya Higuchi, Tomohiko Nakamura, 2014, INTERSPEECH.

Shifted and convolutive source-filter non-negative matrix factorization for monaural audio source separation

Hirokazu Kameoka, Tomohiko Nakamura, H. Kameoka, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bayesian Nonparametric Approach to Blind Separation of Infinitely Many Sparse Sources

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2013, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

Multi-pitch trajectory estimation of concurrent speech based on harmonic GMM and nonlinear kalman filtering

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2004, INTERSPEECH.

Speech Spectrum Modeling for Joint Estimation of Spectral Envelope and Fundamental Frequency

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2010, IEEE Transactions on Audio, Speech, and Language Processing.

Deep acoustic-to-articulatory inversion mapping with latent trajectory modeling

Hirokazu Kameoka, Tomoki Toda, Patrick Lumban Tobing, 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Bayesian Nonparametric Approach to Audio Event Detection

Hirokazu Kameoka, Kunio Kashino, Masahiro Nakano, 2012 .

Composite autoregressive system for sparse source-filter representation of speech

Hirokazu Kameoka, Kunio Kashino, 2009, 2009 IEEE International Symposium on Circuits and Systems.

Resolution Warped Spectral Representation for Low-Delay and Low-Bit-Rate Audio Coder

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Bayesian semi-supervised audio event transcription based on Markov indian buffet process

Hirokazu Kameoka, Kunio Kashino, Masahiro Nakano, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Progress in LPC-based frequency-domain audio coding

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2016 .

Auxiliary function approach to parameter estimation of constrained sinusoidal model for monaural speech separation

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

CycleGAN-VC: Non-parallel Voice Conversion Using Cycle-Consistent Adversarial Networks

Hirokazu Kameoka, Takuhiro Kaneko, H. Kameoka, 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

Spectrogram consistency and its application to phase reconstruction

Hirokazu Kameoka, Shigeki Sagayama, Nobutaka Ono, 2009 .

Automatic Identification for Singing Style based on Sung Melodic Contour Characterized in Phase Plane

Hirokazu Kameoka, Kunio Kashino, Kazuya Takeda, 2009, ISMIR.

ATTS2S-VC: Sequence-to-sequence Voice Conversion with Attention and Context Preservation Mechanisms

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Fast algorithm for statistical phrase/accent command estimation based on generative model incorporating spectral features

Hirokazu Kameoka, Kunio Kashino, Ryotaro Sato, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multichannel Signal Separation Combining Directional Clustering and Nonnegative Matrix Factorization with Spectrogram Restoration

Hirokazu Kameoka, Satoshi Nakamura, Hiroshi Saruwatari, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Supervised Determined Source Separation with Multichannel Variational Autoencoder

Hirokazu Kameoka, Li Li, Shoji Makino, 2019, Neural Computation.

A review of blind source separation methods: two converging routes to ILRMA originating from ICA and NMF

Hirokazu Kameoka, Hiroshi Saruwatari, Daichi Kitamura, 2019, APSIPA Transactions on Signal and Information Processing.

Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression

Hirokazu Kameoka, Masashi Sugiyama, Hitoshi Sakano, 2013 .

Mondrian hidden Markov model for music signal processing

Hirokazu Kameoka, Kunio Kashino, Masahiro Nakano, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

DNN-SPACE: DNN-HMM-Based Generative Model of Voice F0 Contours for Statistical Phrase/Accent Command Estimation

Hirokazu Kameoka, Yusuke Ijima, Nobukatsu Hojo, 2017, INTERSPEECH.

Representation of spectral envelope with warped frequency resolution for audio coder

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2014, 2014 22nd European Signal Processing Conference (EUSIPCO).

Non-negative periodic component analysis for music source separation

Hirokazu Kameoka, Hiroshi Sawada, Aki Hayashi, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform pdf

Hirokazu Kameoka, Junichi Yamagishi, Shinji Takaki, 2019, ArXiv.

Direct Modeling of Frequency Spectra and Waveform Generation Based on Phase Recovery for DNN-Based Speech Synthesis

Hirokazu Kameoka, Junichi Yamagishi, Shinji Takaki, 2017, INTERSPEECH.

Joint Separation and Dereverberation of Reverberant Mixtures with Determined Multichannel Non-Negative Matrix Factorization

Hirokazu Kameoka, Masahiro Yukawa, Hideaki Kagami, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Parameter estimation method of F0 control model for singing voices

Hirokazu Kameoka, Kunio Kashino, Kazuya Takeda, 2008, INTERSPEECH.

SemiCCA: Efficient Semi-supervised Learning of Canonical Correlations

Hirokazu Kameoka, Masashi Sugiyama, Hitoshi Sakano, 2010, International Conference on Pattern Recognition.

Determined Blind Source Separation Unifying Independent Vector Analysis and Nonnegative Matrix Factorization

Hirokazu Kameoka, Hiroshi Sawada, Hiroshi Saruwatari, 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Parameter Estimation Method of F0 Control Model for Singing Voices based on Convolutive HMM

Hirokazu Kameoka, Kunio Kashino, Kazuya Takeda, 2008 .

Explicit beat structure modeling for non-negative matrix factorization-based multipitch analysis

Hirokazu Kameoka, Shigeki Sagayama, Kazuki Ochiai, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Probabilistic Approach to Automatic Music Transcription from Audio Signals

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Discriminative non-negative matrix factorization with majorization-minimization

Li Li, Hirokazu Kameoka, Shoji Makino, 2017, 2017 Hands-free Speech Communications and Microphone Arrays (HSCMA).

I-Divergence-based dereverberation method with auxiliary function approach

Hirokazu Kameoka, Takuya Yoshioka, Hiroshi G. Okuno, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bayesian nonparametric music parser

Hirokazu Kameoka, Kunio Kashino, Masahiro Nakano, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Experimental Evaluation of Superresolution-Based Nonnegative Matrix Factorization for Binaural Recording

Hirokazu Kameoka, Hiroshi Saruwatari, Daichi Kitamura, 2014 .

Harmonic-Temporal Factor Decomposition Incorporating Music Prior Information for Informed Monaural Source Separation

Hirokazu Kameoka, Norihiro Takamune, Tomohiko Nakamura, 2014, ISMIR.

ACVAE-VC: Non-Parallel Voice Conversion With Auxiliary Classifier Variational Autoencoder

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2019, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Music and speech signal processing using harmonic-temporal clustering

Hirokazu Kameoka, Jonathan Le Roux, Alain de Cheveigné, 2008 .

Audio stream segregation of multi-pitch music signal based on time-space clustering using Gaussian kernel 2-dimensional model

Hirokazu Kameoka, Shigeki Sagayama, Takuya Nishimoto, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Hybrid multichannel signal separation using supervised nonnegative matrix factorization with spectrogram restoration

Hirokazu Kameoka, Satoshi Nakamura, Hiroshi Saruwatari, 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.

Mel-Generalized cepstral regularization for discriminative non-negative matrix factorization

Li Li, Hirokazu Kameoka, Shoji Makino, 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

Deep Clustering with Gated Convolutional Networks

Li Li, Hirokazu Kameoka, H. Kameoka, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Probabilistic Modeling of Pitch Contours Toward Prosody Synthesis and Conversion

Hirokazu Kameoka, 2015 .

Training Restricted Boltzmann Machines with auxiliary function approach

Hirokazu Kameoka, Norihiro Takamune, 2014, 2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

Seeing through Sounds: Predicting Visual Semantic Segmentation Results from Multichannel Audio Signals

Hirokazu Kameoka, Kunio Kashino, Go Irie, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Missing component restoration for masked speech signals based on time-domain spectrogram factorization

Hirokazu Kameoka, Tomoki Toda, Kazuya Takeda, 2017, 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP).

The ASVspoof 2019 database pdf

Lauri Juvela, Paavo Alku, Kou Tanaka, 2019, ArXiv.

Optimal Coding of Generalized-Gaussian-Distributed Frequency Spectra for Low-Delay Audio Coder With Powered All-Pole Spectrum Estimation

Hirokazu Kameoka, Takehiro Moriya, Noboru Harada, 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Pretraining Techniques for Sequence-to-Sequence Voice Conversion pdf

Hirokazu Kameoka, Tomoki Toda, Yi-Chiao Wu, 2020, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Multi-resolution signal decomposition with time-domain spectrogram factorization

Hirokazu Kameoka, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Generative modeling of speech F0 contours

Hirokazu Kameoka, Kunio Kashino, Shigeki Sagayama, 2013, INTERSPEECH.

Gaussian model based multichannel separation

Hirokazu Kameoka, Alexey Ozerov, 2017 .

General Formulation of Multichannel Extensions of NMF Variants

Hirokazu Kameoka, Takuya Higuchi, Hiroshi Sawada, 2018 .

Automatic Speech Pronunciation Correction with Dynamic Frequency Warping-Based Spectral Conversion

Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

Statistical F0 prediction for electrolaryngeal speech enhancement considering generative process of F0 contours within product of experts framework

Kou Tanaka, Hirokazu Kameoka, Tomoki Toda, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Hirokazu Kameoka, Shoji Makino, Li Li, 2021, ArXiv.

SepNet: A Deep Separation Matrix Prediction Network for Multichannel Audio Source Separation

Hirokazu Kameoka, Shoji Makino, Li Li, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, 2021, ArXiv.

Many-to-Many Voice Transformer Network

Hirokazu Kameoka, Tomoki Toda, Takuhiro Kaneko, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

X-DC: Explainable Deep Clustering Based on Learnable Spectrogram Templates

Hirokazu Kameoka, Chihiro Watanabe, 2021, Neural Computation.

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

Hirokazu Kameoka, Tadahiro Taniguchi, Shoki Sakamoto, 2021, Interspeech 2021.

Maskcyclegan-VC: Learning Non-Parallel Voice Conversion with Filling in Frames

Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Single-Channel Multispeaker Separation with Variational Autoencoder Spectrogram Model

Hirokazu Kameoka, Shoji Makino, Li Li, 2021, Journal of Signal Processing.

StarGAN-based Emotional Voice Conversion for Japanese Phrases pdf

Hirokazu Kameoka, Tadahiro Taniguchi, Shoki Sakamoto, 2021, ArXiv.

Multichannel Extensions of Nonnegative Matrix Factorization

Hirokazu Kameoka, Naonori Ueda, Hiroshi Sawada, 2012 .

Underdetermined BSS with multichannel complex NMF assuming W-disjoint orthogonality of source

Hirokazu Kameoka, Hiroshi Sawada, Shoko Araki, 2011, TENCON 2011 - 2011 IEEE Region 10 Conference.

Complex NMF under spectrogram consistency constraints

Hirokazu Kameoka, Kunio Kashino, Jonathan Le Roux, 2009 .

Consistent Wiener filtering: designing generalized time-frequency masks respecting spectrogram consistency

Hirokazu Kameoka, Jonathan Le Roux, Emmanuel Vincent, 2010 .