Toru Nakashika

62 papers A 14B 2C 4Misc 8Journal 18Unranked 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Power-Weighted Noncentral Complex Gaussian Distribution. CoRR Toru Nakashika
2025	J	`jnl`	Chord Recognition Considering All Interval RelationsUsing Weight-Sharing Classification Semi-Restricted Boltzmann Machines. IEICE Trans. Inf. Syst. Shunya Ishikawa, Toru Nakashika
2025	—	`conf`	Continuous Speech Prediction by Segmentation of Auditory EEG. EUSIPCO Tomoaki Mizuno, Toru Nakashika, Natsue Yoshimura
2025	J	`jnl`	Fast and Lightweight Non-Parallel Voice Conversion Based on Free-Energy Minimization of Speaker-Conditional Restricted Boltzmann Machine. IEICE Trans. Inf. Syst. Takuya Kishida, Toru Nakashika
2025	—	`conf`	Few-Step Diffusion-Based Voice Conversion Using Consistency Trajectory Models. APSIPA Ryuichi Hatakeyama, Toru Nakashika, Takuya Takahashi
2025	—	`conf`	Gamma-VAE-VC: Voice Conversion based on VAE Assuming Gamma Distribution for Both Latent Variables and Observation. APSIPA Nanako Imaichi, Takuya Takahashi, Toru Nakashika
2025	—	`conf`	Transferability of Adversarial Examples Across Speaker Embedding Models for Voice Privacy Protection. APSIPA Kotaro Nakamura, Takuya Takahashi, Toru Nakashika
2025	—	`conf`	VICNet: FaderNet-Based Voice Impression Conversion with Affective Dimensional Representation. APSIPA Takuya Takahashi, Saki Kugimoto, Toru Nakashika
2025	—	`conf`	Voice Privacy Protection with Adversarial Examples Using Anchor Speaker Embedding. APSIPA Shunya Ishikawa, Yuki Katsumata, Toru Nakashika
2024	—	`conf`	An Investigation on the Speech Recovery from EEG Signals Using Transformer. APSIPA Tomoaki Mizuno, Takuya Kishida, Natsue Yoshimura, Toru Nakashika
2024	—	`conf`	DDPMVC: Non-parallel any-to-many voice conversion using diffusion encoder. APSIPA Ryuichi Hatakeyama, Kohei Okuda, Toru Nakashika
2024	—	`conf`	Gamma-VAE: Speech representation based on VAE assuming gamma distribution for both latent variables and observation. APSIPA Nanako Imaichi, Toru Nakashika
2021	C	`conf`	Acoustic Scenery Recognition Using CWT and Deep Neural Network. SoMeT Francisco Mondragon, Jonathan Jimenez, Mariko Nakano, Toru Nakashika, Héctor Pérez-Meana
2021	J	`jnl`	Gamma Boltzmann Machine for Audio Modeling. IEEE ACM Trans. Audio Speech Lang. Process. Toru Nakashika, Kohei Yatabe
2020	A	`conf`	Complex-Valued Variational Autoencoder: A Novel Deep Generative Model for Direct Representation of Complex Spectra. INTERSPEECH Toru Nakashika
2020	—	`conf`	Gamma Boltzmann Machine for Simultaneously Modeling Linear- and Log-amplitude Spectra. APSIPA Toru Nakashika, Kohei Yatabe
2020	J	`jnl`	Gamma Boltzmann Machine for Simultaneously Modeling Linear- and Log-amplitude Spectra. CoRR Toru Nakashika, Kohei Yatabe
2020	C	`conf`	Many-to-Many Symbolic Multi-Track Music Genre Transfer. SoMeT Michel Pezzat, Héctor Manuel Pérez Meana, Toru Nakashika, Mariko Nakano
2020	A	`conf`	Simultaneous Conversion of Speaker Identity and Emotion Based on Multiple-Domain Adaptive RBM. INTERSPEECH Takuya Kishida, Shin Tsukamoto, Toru Nakashika
2020	J	`jnl`	Speech Chain VC: Linking Linguistic and Acoustic Levels via Latent Distinctive Features for RBM-Based Voice Conversion. IEICE Trans. Inf. Syst. Takuya Kishida, Toru Nakashika
2019	J	`jnl`	Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra. IEEE ACM Trans. Audio Speech Lang. Process. Toru Nakashika, Shinji Takaki, Junichi Yamagishi
2019	J	`jnl`	Non-parallel dictionary learning for voice conversion using non-negative Tucker decomposition. EURASIP J. Audio Speech Music. Process. Yuki Takashima, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2019	J	`jnl`	Pre-Training of DNN-Based Speech Synthesis Based on Bidirectional Conversion between Text and Speech. IEICE Trans. Inf. Syst. Kentaro Sone, Toru Nakashika
2019	Misc	`conf`	STFT Spectral Loss for Training a Neural Speech Waveform Model. ICASSP Shinji Takaki, Toru Nakashika, Xin Wang, Junichi Yamagishi
2018	—	`conf`	Bidirectional Voice Conversion Based on Joint Training Using Gaussian-Gaussian Deep Relational Model. Odyssey Kentaro Sone, Shinji Takaki, Toru Nakashika
2018	J	`jnl`	Complex-Valued Restricted Boltzmann Machine for Direct Speech Parameterization from Complex Spectra. CoRR Toru Nakashika, Shinji Takaki, Junichi Yamagishi
2018	A	`conf`	DNN-based Speech Synthesis for Small Data Sets Considering Bidirectional Speech-Text Conversion. INTERSPEECH Kentaro Sone, Toru Nakashika
2018	J	`jnl`	Deep Relational Model: A Joint Probabilistic Model with a Hierarchical Structure for Bidirectional Estimation of Image and Labels. IEICE Trans. Inf. Syst. Toru Nakashika
2018	A	`conf`	LSTBM: A Novel Sequence Representation of Speech Spectra Using Restricted Boltzmann Machine with Long Short-Term Memory. INTERSPEECH Toru Nakashika
2018	Misc	`conf`	Parallel-Data-Free Dictionary Learning for Voice Conversion Using Non-Negative Tucker Decomposition. ICASSP Yuki Takashima, Hajime Yano, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2018	J	`jnl`	STFT spectral loss for training a neural speech waveform model. CoRR Shinji Takaki, Toru Nakashika, Xin Wang, Junichi Yamagishi
2017	A	`conf`	CAB: An Energy-Based Speaker Clustering Model for Rapid Adaptation in Non-Parallel Voice Conversion. INTERSPEECH Toru Nakashika
2017	A	`conf`	Complex-Valued Restricted Boltzmann Machine for Direct Learning of Frequency Spectra. INTERSPEECH Toru Nakashika, Shinji Takaki, Junichi Yamagishi
2017	J	`jnl`	Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion. EURASIP J. Audio Speech Music. Process. Toru Nakashika, Yasuhiro Minami
2016	—	`conf`	3WRBM-based speech factor modeling for arbitrary-source and non-parallel voice conversion. EUSIPCO Toru Nakashika, Yasuhiro Minami
2016	A	`conf`	Generative Acoustic-Phonemic-Speaker Model Based on Three-Way Restricted Boltzmann Machine. INTERSPEECH Toru Nakashika, Yasuhiro Minami
2016	Misc	`conf`	Modeling deep bidirectional relationships for image classification and generation. ICASSP Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2016	J	`jnl`	Non-Parallel Training in Voice Conversion Using an Adaptive Restricted Boltzmann Machine. IEEE ACM Trans. Audio Speech Lang. Process. Toru Nakashika, Tetsuya Takiguchi, Yasuhiro Minami
2016	C	`conf`	Selection of an optimum random matrix using a genetic algorithm for acoustic feature extraction. ICIS Yuichiro Kataoka, Toru Nakashika, Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki
2016	Misc	`conf`	Speaker adaptive model based on Boltzmann machine for non-parallel training in voice conversion. ICASSP Toru Nakashika, Yasuhiro Minami
2015	B	`conf`	Content-based Image Retrieval Using Rotation-invariant Histograms of Oriented Gradients. ICMR Jinhui Chen, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2015	—	`conf`	Feature extraction using pre-trained convolutive bottleneck nets for dysarthric speech recognition. EUSIPCO Yuki Takashima, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2015	—	`conf`	Noise-robust voice conversion using a small parallel data based on non-negative matrix factorization. EUSIPCO Ryo Aihara, Takao Fujii, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2015	J	`jnl`	Small-parallel exemplar-based voice conversion in noisy environments using affine non-negative matrix factorization. EURASIP J. Audio Speech Music. Process. Ryo Aihara, Takao Fujii, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2015	A	`conf`	Sparse nonlinear representation for voice conversion. ICME Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2015	J	`jnl`	Voice Conversion Using RNN Pre-Trained by Recurrent Temporal Restricted Boltzmann Machines. IEEE ACM Trans. Audio Speech Lang. Process. Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2015	J	`jnl`	Voice conversion using speaker-dependent conditional restricted Boltzmann machine. EURASIP J. Audio Speech Music. Process. Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2014	B	`conf`	3D-Object Recognition Based on LLC Using Depth Spatial Pyramid. ICPR Toru Nakashika, Takafumi Hori, Tetsuya Takiguchi, Yasuo Ariki
2014	A	`conf`	Error correction of automatic speech recognition based on normalized web distance. INTERSPEECH E. Byambakhishig, Katsuyuki Tanaka, Ryo Aihara, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2014	A	`conf`	High-order sequence modeling using speaker-dependent recurrent temporal restricted boltzmann machines for voice conversion. INTERSPEECH Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2014	J	`jnl`	Voice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines. IEICE Trans. Inf. Syst. Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2014	Misc	`conf`	Voice conversion based on Non-negative matrix factorization using phoneme-categorized dictionary. ICASSP Ryo Aihara, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2014	Misc	`conf`	Voice conversion in time-invariant speaker-independent space. ICASSP Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2013	C	`conf`	A Combination of Hand-Crafted and Hierarchical High-Level Learnt Feature Extraction for Music Genre Classification. ICANN Julien N. P. Martel, Toru Nakashika, Christophe Garcia, Khalid Idrissi
2013	—	`conf`	High-Frequency Restoration Using Deep Belief Nets for Super-resolution. SITIS Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2013	Misc	`conf`	Sparse representation for outliers suppression in semi-supervised image annotation. ICASSP Toru Nakashika, Takeshi Okumura, Tetsuya Takiguchi, Yasuo Ariki
2013	A	`conf`	Voice conversion in high-order eigen space using deep belief nets. INTERSPEECH Toru Nakashika, Ryoichi Takashima, Tetsuya Takiguchi, Yasuo Ariki
2012	A	`conf`	Local-feature-map Integration Using Convolutional Neural Networks for Music Genre Classification. INTERSPEECH Toru Nakashika, Christophe Garcia, Tetsuya Takiguchi
2011	—	`conf`	Constrained Spectrum Generation Using A Probabilistic Spectrum Envelope for Mixed Music Analysis. ISMIR Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2011	Misc	`conf`	Generic object recognition using automatic region extraction and dimensional feature integration utilizing multiple kernel learning. ICASSP Toru Nakashika, Akira Suga, Tetsuya Takiguchi, Yasuo Ariki
2011	A	`conf`	Probabilistic Spectrum Envelope: Categorized Audio-Features Representation for NMF-Based Sound Decomposition. INTERSPEECH Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
2010	A	`conf`	Speech synthesis by modeling harmonics structure with multiple function. INTERSPEECH Toru Nakashika, Ryuki Tachibana, Masafumi Nishimura, Tetsuya Takiguchi, Yasuo Ariki