Publications

2014

Conference Proceedings (peer reviewed)

Speaker Adaptation of Deep Neural Networks Using a Hierarchy of Output Layers
Ryan Price, Kenichi Iso, Koichi Shinoda
Proc. Spoken Language Technology (SLT) Workshop, pp. 153-158, Dec. 7, 2014

An Efficient Error Correction Interface for Speech Recognition on Mobile Touchscreen Devices
Yuan Liang, Koji Iwano, Koichi Shinoda
Proc. Spoken Language Technology (SLT) Workshop, pp. 454-459, Dec. 7, 2014

n-Gram Models for Video Semantic Indexing
Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia (MM), pp. 777-780, Nov. 3, 2014

Spectral Graph Skeletons for 3D Action Recognition
Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
Proc. Asian Conference on Computer Vision (ACCV), pp. 1-16, Nov. 1, 2014

Simple Gesture-based Error Correction Interface for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
Proc. Interspeech, pp. 1194-1198, Sep. 16, 2014

Discriminative PLDA training with application-specific loss functions for speaker verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. Odyssey Workshop, pp. 26-32, Jun. 16, 2014

i-Vector Selection for Effective PLDA Modeling in Speaker Recognition
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
Proc. Odyssey Workshop, pp. 100-105, Jun. 16, 2014

Constrained Discriminative PLDA Training for Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. International Conference on Acoustic Speech and Signal Processing (ICASSP), pp. 1689-1693, May 4, 2014

Event Detection by Velocity Pyramid
Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda
Proc. Multimedia Modeling (MMM), pp. 353-364, Jan. 6, 2014

Conference Proceedings (non-refereed)

TokyoTech-Waseda at TRECVID 2014
Nakamasa Inoue, Zhuolin Liang, Mengxi Lin, Tran Hai Dang, Koichi Shinoda, Zhang Xuefeng, Kazuya Ueki
Proc. TRECVID workshop, pp. 1-13, Nov. 9, 2014

Domestic Conference Proceedings

Error Correction Using Long Context Match for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
Technical Reports of IPSJ SLP, vol. 104, no. 22, pp. 1-6, Dec. 16, 2014

An Efficient Error Correction Method for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
Proc. ASJ 2014 Autumn Meeting, pp. 29-30, Sep. 5, 2014

Collection and analysis of multi-party interaction data for automatic boredom recognition
Nataliia Biriukova, Kotaro Funakoshi, Koichi Shinoda
Proc. The 28th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI) 2014, pp. 1-4, May 13, 2014

Velocity Pyramid for Event Detection
Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IEICE PRMU, vol. 113, no. 493, pp. 13-18, Mar. 13, 2014

Discriminatively Trained PLDA with Partially Preserved Model Assumptions in Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. ASJ 2014 Spring Meeting, pp. 99-100, Mar. 12, 2014

Training Multiple PLDA Models by Clustered I-Vectors for Speaker Verification
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
Proc. ASJ 2014 Spring Meeting, pp. 97-98, Mar. 12, 2014

Robust 0-1 Loss Training for PLDA in Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. ASJ 2014 Spring Meeting, pp. 101-102, Mar. 12, 2014

Invited Talks & Tutorials

Robust Video Information Retrieval using Speech Technologies
Koichi Shinoda
Language Technologies Institute, Carnegie Mellon University, Jun. 20, 2014

Video Semantic Indexing Using Speech Technologies
Koichi Shinoda
Dublin City University, Jan. 6, 2014

Selected Talks

Semantics for Large-Scale Multimedia: New Challenges for NLP
Florian Metze, Koichi Shinoda
ACL2014, Jun. 22, 2014