論文
公開件数:60件
No. 種別 査読の有無 標題 単著・共著区分 著者 誌名 巻号頁 出版日 ISSN DOI URL
1 一般論文

Gamma Boltzmann Machine for Audio Modeling
共著
Toru Nakashika, Kohei Yatabe
IEEE/ACM Transactions on Audio, Speech and Language Processing
29, 2591-2605
2021/07/08

10.1109/TASLP.2021.3095656

2 一般論文

Speech chain VC: linking linguistic and acoustic levels via latent distinctive features for RBM-based voice conversion
共著
Takuya Kishida, Toru Nakashika
IEICE TRANSACTIONS on Information and Systems
E103-D/ 11, 1-11
2020/08/06
1745-1361
10.1587/transinf.2020EDP7032

3 一般論文

Non-parallel dictionary learning for voice conversion using non-negative Tucker decomposition
共著
Yuki Takashima, Toru Nakashika, Tetsuya Takiguchi and Yasuo Ariki
EURASIP Journal on Audio, Speech, and Music Processing
DOI: 10.1186/s13636-019-0160-1, 1-11
2019/08/14

10.1186/s13636-019-0160-1

4 一般論文

Pre-Training of DNN-Based Speech Synthesis Based on Bidirectional Conversion between Text and Speech
共著
Kentaro Sone, Toru Nakashika
IEICE TRANSACTIONS on Information and Systems
E102-D/ 8, 1546-1553
2019/08/01
1745-1361
10.1587/transinf.2018EDP7344

5 一般論文

Complex-Valued Restricted Boltzmann Machine for Speaker-Dependent Speech Parameterization From Complex Spectra
共著
Toru Nakashika, Shinji Takaki, Junichi Yamagishi
IEEE/ACM Transactions on Audio, Speech and Language Processing
27/ 2, 244-254
2018/10/22
2329-9290
10.1109/TASLP.2018.2877465

6 一般論文

Deep Relational Model: A Joint Probabilistic Model with a Hierarchical Structure for Bidirectional Estimation of Image and Labels
共著
Toru Nakashika
IEICE Transactions on Information and Systems
E101-D/ 2, 428-436
2018/02/01

10.1587/transinf.2017EDP7149

7 一般論文

Speaker-adaptive-trainable Boltzmann machine and its application to non-parallel voice conversion
共著
Toru Nakashika, Yasuhiro Minami
EURASIP Journal on Audio, Speech, and Music Processing
DOI: 10.1186/s13636-017-0112-6, 1-10
2017/06/29



8 一般論文

Non-Parallel Training in Voice Conversion Using an
Adaptive Restricted Boltzmann Machine
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuhiro Minami
IEEE/ACM Transactions on Audio, Speech and Language Processing
24/ 11, 2032-2045
2016/08

10.1109/TASLP.2016.2593263

9 一般論文

Phone Labeling Based on the Probabilistic Representation for Dysarthric Speech Recognition
共著
Yuki Takashima, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
American Journal of Signal Processing
6/ 1, 19-23
2016/06



10 一般論文

Small-parallel exemplar-based voice conversion in noisy environments using affine non-negative matrix factorization
共著
Ryo Aihara, Takao Fujii, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
EURASIP Journal on Audio, Speech, and Music Processing
2015:32/ DOI: 10.1186/s13636-015-0075-4, 1-9
2015/11/25



11 一般論文

Voice Conversion Using RNN Pre-Trained by Recurrent Temporal Restricted Boltzmann Machines
共著
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
IEEE/ACM Transactions on Audio, Speech and Language Processing
23/ 3, 580-587
2015/03



12 一般論文

Voice conversion using speaker-dependent conditional restricted Boltzmann machine
共著
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
EURASIP Journal on Audio, Speech, and Music Processing
2015:8/ DOI 10.1186/s13636-014-0044-3, 1-12
2015/02



13 一般論文

Probabilistic spectral envelope modeling of musical instruments within the non-negative matrix factorization framework for mixed music analysis
共著
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Acoustical Science and Technology
35/ 4, 181-191
2014/07



14 一般論文

Parallel Dictionary Learning Using a Joint Density Restricted Boltzmann Machine for Sparse-Representation-Based Voice Conversion
共著
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
Advances in Computer Science and Engineering
12/ 2, 101-117
2014/06



15 一般論文

Voice Conversion Based on Speaker-Dependent Restricted Boltzmann Machines
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
IEICE Transactions on Information and Systems
E97-D/ 6, 1403-1410
2014/06



16 一般論文

Depth Spatial Pyramid: a Pooling Method for 3D-Object Recognition
共著
Toru Nakashika, Takafumi Hori, Tetsuya Takiguchi, and Yasuo Ariki
Advances in Computer Science and Engineering
12/ 1, 15-30
2014/04



17 一般論文

Convolutive Bottleneck Network with Dropout for Dysarthric Speech Recognition
共著
Toru Nakashika, Toshiya Yoshioka, Tetsuya Takiguchi, Yasuo Ariki, Stefan Duffner, Christophe Garcia
Transactions on Machine Learning and Artificial Intelligence
2/ 2, 48-62
2014/04



18 一般論文

Hierarchical Sparse Representation for Object Recognition
共著
Toru Nakashika, Takeshi Okumura, Tetsuya Takiguchi, Yasuo Ariki
Transactions on Machine Learning and Artificial Intelligence
2/ 1, 46-60
2014/02



19 一般論文

Mixed Music Analysis with Extended Specmurt
共著
Daiki Nishimura, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Journal of software engineering and applications
6/ 5, 274-279
2013/05



20 一般論文

Sparseness Criteria of F0-Frequencies Selection for Specmurt-Based Multi-Pitch Analysis without Modeling Harmonic Structure
共著
Daiki Nishimura, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Journal of Signal Processing
17/ 2, 29-38
2013/03



21 国際会議プロシーディングス等

Gamma Boltzmann Machine for Simultaneously Modeling Linear- and Log-amplitude Spectra
共著
Toru Nakashika and Kohei Yatabe
Proceedings of APSIPA Annual Summit and Conference 2020
471-476
2020/12



22 国際会議プロシーディングス等

Simultaneous Conversion of Speaker Identity and Emotion Based on Multiple-Domain Adaptive RBM
共著
Takuya Kishida, Shin Tsukamoto, Toru Nakashika
Proceedings of the Interspeech 2020
3431-3435
2020/10



23 国際会議プロシーディングス等

Complex-Valued Variational Autoencoder: A Novel Deep Generative Model for Direct Representation of Complex Spectra
共著
Toru Nakashika
Proceedings of the Interspeech 2020
2002-2006
2020/10



24 国際会議プロシーディングス等

Many-to-Many Symbolic Multi-track Music Genre Transfer
共著
Michel Pezzat, Hector Perez-Meana, Toru Nakashika, Mariko Nakano
Proceedings of the SoMeT 2020
272-281
2020/09



25 国際会議プロシーディングス等

STFT spectral loss for training a neural speech waveform model
共著
Shinji Takaki, Toru Nakashika, Xin Wang, Junichi Yamagishi
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019)
7065-7069
2019/05



26 国際会議プロシーディングス等

LSTBM: A Novel Sequence Representation of Speech Spectra Using Restricted Boltzmann Machine with Long Short-Term Memory
単著
Toru Nakashika
Proceedings of the Interspeech 2018
2529-2533
2018/09



27 国際会議プロシーディングス等

DNN-based Speech Synthesis for Small Data Sets Considering Bidirectional Speech-Text Conversion
共著
Kentaro Sone, and Toru Nakashika
Proceedings of the Interspeech 2018
2519-2523
2018/09



28 国際会議プロシーディングス等

Bidirectional Voice Conversion Based on Joint Training Using Gaussian-Gaussian Deep Relational Model
共著
Kentaro Sone, Shinji Takaki, and Toru Nakashika
Proceedings of the Odyssey 2018
261-266
2018/06



29 国際会議プロシーディングス等

Parallel-Data-Free Dictionary Learning for Voice Conversion Using Non-Negative Tucker Decomposition
共著
Yuki Takashima, Hajime Yano, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)
5294-5298
2018/04



30 国際会議プロシーディングス等

Complex-valued restricted Boltzmann machine for direct learning of frequency spectra
共著
Toru Nakashika, Shinji Takaki, and Junichi Yamagishi
Proceedings of the 18th Conference of the International Speech Communication Association (Interspeech 2017)
4021-4025
2017/08



31 国際会議プロシーディングス等

CAB: An Energy-Based Speaker Clustering Model for Rapid Adaptation in Non-Parallel Voice Conversion
単著
Toru Nakashika
Proceedings of the 18th Conference of the International Speech Communication Association (Interspeech 2017)
3369-3373
2017/08



32 国際会議プロシーディングス等

Emotional Voice Conversion Using Neural Networks with Different Temporal Scales of F0 based on Wavelet Transform
共著
Zhaojie Luo, Jinhui Chen, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
The 9th ISCA Speech Synthesis Workshop (SSW)
153-158
2016/09



33 国際会議プロシーディングス等

Generative Acoustic-Phonemic-Speaker Model Based on Three-Way Restricted Boltzmann Machine
共著
Toru Nakashika, and Yasuhiro Minami
Proceedings of the 17th Conference of the International Speech Communication Association (Interspeech 2016)
1487-1491
2016/09



34 国際会議プロシーディングス等

3WRBM-Based Speech Factor Modeling for Arbitrary-Source and Non-Parallel Voice Conversion
共著
Toru Nakashika, and Yasuhiro Minami
The 24th European Signal Processing Conference (EUSIPCO)
607-611
2016/08



35 国際会議プロシーディングス等

Selection of an Optimum Random Matrix Using a Genetic Algorithm for Acoustic Feature Extraction
共著
Yuichiro Kataoka, Toru Nakashika, Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 15th IEEE/ACIS International Conference on Computer and Information Science (ICIS 2016)
983-988
2016/06



36 国際会議プロシーディングス等

Speaker Adaptive Model Based on Boltzmann Machine for Non-Parallel Training in Voice Conversion
共著
Toru Nakashika, Yasuhiro Minami
Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)
5530-5534
2016/03



37 国際会議プロシーディングス等

Modeling Deep Bidirectional Relationships for Image Classification and Generation
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016)
1327-1331
2016/03



38 国際会議プロシーディングス等

Parallel-Data-Free, Many-to-Many Voice Conversion Using an Adaptive Restricted Boltzmann Machine
共著
Toru Nakashika, Tetsuya Takiguchi and Yasuo Ariki
MLSLP 2015
1-6
2015/09



39 国際会議プロシーディングス等

Feature Extraction Using Pre-Trained Convolutive Bottleneck Nets for Dysarthric Speech Recognition
共著
Yuki Takashima, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
The 23rd European Signal Processing Conference (EUSIPCO)
1426-1430
2015/08



40 国際会議プロシーディングス等

Noise-Robust Voice Conversion Using a Small Parallel Data Based on Non-Negative Matrix Factorization
共著
Ryo Aihara, Takao Fujii, Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
The 23rd European Signal Processing Conference (EUSIPCO)
315-319
2015/08



41 国際会議プロシーディングス等

Sparse Nonlinear Representation for Voice Conversion
共著
Toru Nakashika, Tetsuya Takiguchi and Yasuo Ariki
IEEE ICME 2015
1-6
2015/06



42 国際会議プロシーディングス等

Dysarthric Speech Recognition Using a Convolutive Bottleneck Network
共著
Toru Nakashika, Toshiya Yoshioka, Tetsuya Takiguchi, Yasuo Ariki, Stefan Duffner, Christophe Garcia
Proceedings of the 12th IEEE International Conference on Signal Processing (ICSP'14)
505-509
2014/10



43 国際会議プロシーディングス等

Error Correction of Automatic Speech Recognition Based on Normalized Web Distance
共著
E. Byambakhishig, K. Tanaka, R. Aihara, T. Nakashika, T. Takiguchi, Y. Ariki
Proceedings of the 15th Conference of the International Speech Communication Association (Interspeech 2014)
2852-2856
2014/09



44 国際会議プロシーディングス等

High-Order Sequence Modeling Using Speaker-Dependent Recurrent Temporal Restricted Boltzmann Machines for Voice Conversion
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 15th Conference of the International Speech Communication Association (Interspeech 2014)
2278-2282
2014/09



45 国際会議プロシーディングス等

3D-Object Recognition Based on LLC Using Depth Spatial Pyramid
共著
Toru Nakashika, Takafumi Hori, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 23st International Conference on Pattern Recognition (ICPR 2014)
4224-4228
2014/08



46 国際会議プロシーディングス等

Voice Conversion in Time-Invariant Speaker-Independent Space
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 39th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)
7939-7943
2014/05



47 国際会議プロシーディングス等

Voice Conversion Based on Non-Negative Matrix Factorization Using Phoneme-Categorized Dictionary
共著
Ryo Aihara, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 39th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2014)
7944-7948
2014/05



48 国際会議プロシーディングス等

High-frequency Restoration Using Deep Belief Nets for Super-resolution
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 9th International Conference on Signal Image Technology & Internet-Based Systems (SITIS 2013)
38-42
2013/12



49 国際会議プロシーディングス等

A Combination of Hand-crafted and Hierarchical High-level Learnt Feature Extraction for Music Genre Classification
共著
Julien Martel, Toru Nakashika, Christophe Garcia, Khalid Idrissi
Proceedings of the 23rd International Conference on Artificial Neural Networks (ICANN 2013)
397-404
2013/09



50 国際会議プロシーディングス等

Voice Conversion in High-order Eigen Space Using Deep Belief Nets
共著
Toru Nakashika, Ryoichi Takashima, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 14th Conference of the International Speech Communication Association (Interspeech 2013)
369-372
2013/08



51 国際会議プロシーディングス等

Sparse Representation for Outliers Suppression in Semi-supervised Image Annotation
共著
Toru Nakashika, Takeshi Okumura, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 38th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013)
2080-2083
2013/05



52 国際会議プロシーディングス等

Local-feature-map Integration Using Convolutional Neural Networks for Music Genre Classification
共著
Toru Nakashika, Christophe Garcia, Tetsuya Takiguchi
Proceedings of the 13th Conference of the International Speech Communication Association (Interspeech 2012)
1-4
2012/09



53 国際会議プロシーディングス等

Constrained Spectrum Generation Using A Probabilistic Spectrum Envelope for Mixed Music Analysis
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 12th International Society for Music Information Retrieval Conference (ISMIR 2011)
181-184
2011/10



54 国際会議プロシーディングス等

Probabilistic Spectrum Envelope: Categorized Audio-features Representation for NMF-based Sound Decomposition
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 12th Conference of the International Speech Communication Association (Interspeech 2011)
1765-1768
2011/08



55 国際会議プロシーディングス等

Generic Object Recognition Using Automatic Region Extraction and Dimensional Feature Integration Utilizing Multiple Kernel Learning
共著
Toru Nakashika, Akira Suga, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 36th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2011)
1229-1232
2011/05



56 国際会議プロシーディングス等

Harmonic-Temporal Model with Multiple Function for Sound Synthesis
共著
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Abstracts of the 161st Meeting of the Acoustical Society of America
2582-2582
2011/05



57 国際会議プロシーディングス等

Multi-pitch Analysis with Specmurt Based on the Sparseness of the Common Harmonic Structure Pattern
共著
Daiki Nishimura, Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki
Abstracts of the 161st Meeting of the Acoustical Society of America
2582-2582
2011/05



58 国際会議プロシーディングス等

Speech Synthesis by Modeling Harmonics Structure with Multiple Function
共著
Toru Nakashika, Ryuki Tachibana, Masafumi Nishimura, Tetsuya Takiguchi, Yasuo Ariki
Proceedings of the 11th Conference of the International Speech Communication Association (Interspeech 2010)
945-948
2010/09



59 国際会議プロシーディングス等

Mathematical Modeling of Harmonic-Timbre Structure with Multi-Beta-Distribution
共著
Toru Nakashika, Tetsuya Takiguchi, and Yasuo Ariki
IEEE Statistical Signal Processing Workshop 2009
769-772
2010/08



60 解説

複素数の観測データを直接表現する制限ボルツマンマシンの拡張と音声信号処理への応用
単著
中鹿 亘
日本音響学会誌
75/ 3, 164-172
2019/03/01
0369-4232