Toru Nakashika's Page

Journal Papers

2015

Ryo Aihara, Takao Fujii, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Small-parallel exemplar-based voice conversion in noisy environments using affine non-negative matrix factorization link
EURASIP Journal on Audio, Speech, and Music Processing 2015, 2015:32, DOI:10.1186/s13636-015-0075-4, 9 pages, November 2015.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Voice conversion using speaker-dependent conditional restricted Boltzmann machine link
EURASIP Journal on Audio, Speech, and Music Processing 2015, 2015:8, DOI:10.1186/s13636-014-0044-3, 12 pages, February 2015.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Voice Conversion Using RNN Pre-Trained by Recurrent Temporal Restricted Boltzmann Machines link
IEEE/ACM Transactions on Audio, Speech and Language Processing, Vol.23, No.3, pp.580-587, March 2015.

2014

Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Probabilistic spectral envelope modeling of musical instruments within the non-negative matrix factorization framework for mixed music analysis link
Acoustical Science and Technology, Vol.35, No.4, pp.181-191, July 2014.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Parallel Dictionary Learning Using a Joint Density Restricted Boltzmann Machine for Sparse-Representation-Based Voice Conversion
Advances in Computer Science and Engineering, Vol.12, No.2, pp.101-117, June 2014.
Toru Nakashika, Toshiya Yoshioka, Tetsuya Takiguchi, Yasuo Ariki, Stefan Duffner, and Christophe Garcia
Convolutive Bottleneck Network with Dropout for Dysarthric Speech Recognition
Transactions on Machine Learning and Artificial Intelligence, Vol.2, No.2, pp.46-60, April 2014.
Toru Nakashika, Takeshi Okumura, Tetsuya Takiguchi, and Yasuo Ariki
Hierarchical Sparse Representation for Object Recognition
Transactions on Machine Learning and Artificial Intelligence, Vol.2, No.1, pp.46-60, February 2014.
Toru Nakashika, Takafumi Hori, Tetsuya Takiguchi, and Yasuo Ariki

Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Voice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines
IEICE Transactions on Information and Systems, Vol.E97-D, No.6, pp.1403-1410, June 2014.

2013

Daiki Nishimura, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Mixed Music Analysis with Extended Specmurt
Journal of software engineering and applications, Volume 6, Number 5, pp. 274-279, May 2013.
Daiki Nishimura, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Sparseness Criteria of F0-Frequencies Selection for Specmurt-Based Multi-Pitch Analysis without Modeling Harmonic Structure
Journal of Signal Processing, Vol. 17, No. 2, pp.29-38, March 2013

International Conferences

2015

Toru Nakashika, and Yasuhiro Minami
Speaker Adaptive Model Based on Boltzmann Machine for Non-Parallel Training in Voice Conversion
ICASSP2016, pp.5530-5534, 2016-03.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Modeling Deep Bidirectional Relationships for Image Classification and Generation
ICASSP2016, pp.1327-1331, 2016-03.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Parallel-Data-Free, Many-To-Many Voice Conversion Using an Adaptive Restricted Boltzmann Machine pdf
MLSLP 2015, 6 pages, September 2015.
Yuki Takashima, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Feature Extraction Using Pre-Trained Convolutive Bottleneck Nets for Dysarthric Speech Recognition
The 23rd European Signal Processing Conference (EUSIPCO), pp. 1426-1430, August 2015.
Ryo Aihara, Takao Fujii, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Noise-Robust Voice Conversion Using a Small Parallel Data Based on Non-Negative Matrix Factorization
The 23rd European Signal Processing Conference (EUSIPCO), pp. 315-319, August 2015.
Jinhui Chen, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Content-based Image Retrieval Using Rotation-invariant Histograms of Oriented Gradients
ACM ICMR 2015, pp. 443-446, Shanghai, June 2015.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Sparse Nonlinear Representation for Voice Conversion pdf
IEEE ICME 2015, 6 pages, June 2015.

2014

Toru Nakashika, Toshiya Yoshioka, Tetsuya Takiguchi, Yasuo Ariki, Stefan Duffner, and Christophe Garcia
Dysarthric Speech Recognition Using a Convolutive Bottleneck Network pdf
ICSP2014, pp.505-509, 2014-10.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
High-Order Sequence Modeling Using Speaker-Dependent Recurrent Temporal Restricted Boltzmann Machines for Voice Conversion pdf
Interspeech2014, pp.2278-2282, 2014-09.
E. Byambakhishig, K. Tanaka, R. Aihara, T. Nakashika, T. Takiguchi, and Y. Ariki
Error Correction of Automatic Speech Recognition Based on Normalized Web Distance
Interspeech2014, pp.2852-2856, 2014-09.
Toru Nakashika, Takafumi Hori, Tetsuya Takiguchi, Yasuo Ariki
3D-Object Recognition Based on LLC Using Depth Spatial Pyramid pdf
ICPR2014, pp.4224-4228, 2014-08.
Ryo Aihara, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Voice Conversion Based on Non-Negative Matrix Factorization Using Phoneme-Categorized Dictionary
ICASSP2014, pp.7944-7948, 2014-05.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Voice Conversion in Time-Invariant Speaker-Independent Space pdf
ICASSP2014, pp.7939-7943, 2014-05.

2013

Julien Martel, Toru Nakashika, Christophe Garcia, and Khalid Idrissi
A Combination of Hand-crafted and Hierarchical High-level Learnt Feature Extraction for Music Genre Classiﬁcation
International Conference on Artificial Neural Networks (ICANN 2013), Sofia, Bulgaria. pp. 397-404, 2013-09.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
High-frequency Restoration Using Deep Belief Nets for Super-resolution pdf
The 9th International Conference on Signal Image Technology & Internet-Based Systems 2013, pp. 38-42, 2013-12.
Toru Nakashika, Ryoichi Takashima, Tetsuya Takiguchi, and Yasuo Ariki
Voice Conversion in High-order Eigen Space Using Deep Belief Nets pdf
INTERSPEECH 2013, pp.369-372, 2013-08.
Toru Nakashika, Takeshi Okumura, Tetsuya Takiguchi, and Yasuo Ariki
Sparse Representation for Outliers Suppression in Semi-supervised Image Annotation pdf
ICASSP2013, pp.2080-2083, 2013-05.

2012

Toru Nakashika, Christophe Garcia, and Tetsuya Takiguchi
Local-feature-map Integration Using Convolutional Neural Networks for Music Genre Classiﬁcation pdf
INTERSPEECH 2012, 2012-09

2011

Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Constrained Spectrum Generation Using A Probabilistic Spectrum Envelope for Mixed Music Analysis pdf
12th International Society for Music Information Retrieval Conference (ISMIR 2011), pp.181-184, 2011-10.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Probabilistic Spectrum Envelope: Categorized Audio-features Representation for NMF-based Sound Decomposition pdf
INTERSPEECH 2011, pp. 1765-1768, 2011-08.
Daiki Nishimura, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Multi-pitch analysis with specmurt based on the sparseness of the common harmonic structure pattern
161st Meeting of the Acoustical Society of America, 4aMU9, pp. 2582, 2011-05.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Harmonic-temporal model with multiple function for sound synthesis
161st Meeting of the Acoustical Society of America, 4aMU8, pp. 2582, 2011-05.
Toru Nakashika, Akira Suga, Tetsuya Takiguchi, and Yasuo Ariki
Generic Object Recognition Using Automatic Region Extraction and Dimensional Feature Integration Utilizing Multiple Kernel Learning
ICASSP2011, pp. 1229-1232, 2011-05.
Toru Nakashika, Ryuki Tachibana, Masafumi Nishimura, Tetsuya Takiguchi, and Yasuo Ariki
Speech Synthesis by Modeling Harmonics Structure with Multiple Function
INTERSPEECH 2010, pp. 945-948, 2010-09.
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Mathematical Modeling of Harmonic-Timbre Structure with Multi-Beta-Distribution
IEEE Statistical Signal Processing Workshop 2009, pp.769-772, 2009-08.

... and 45 Technical Reports / Domestic Proceedings in Japanese.