Goshu Nagino

User adaptation of convolutional neural network for human activity recognition

Koichi Shinoda, Nakamasa Inoue, Shinya Matsui, 2017, 2017 25th European Signal Processing Conference (EUSIPCO).

Distance measure between Gaussian distributions for discriminating speaking styles

Makoto Shozakai, Goshu Nagino, 2006, INTERSPEECH.

How to judge reusability of existing speech corpora for target task by utilizing statistical multidimensional scaling

Kiyohiro Shikano, Makoto Shozakai, Goshu Nagino, 2007, INTERSPEECH.

Analysis of speaking styles by two-dimensional visualization of aggregate of acoustic models

Makoto Shozakai, Goshu Nagino, 2004, INTERSPEECH.

Building an effective corpus by using acoustic space visualization (COSMOS) method [speech recognition applications]

Makoto Shozakai, Goshu Nagino, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Improving robustness of speech recognition performance to aggregate of noises by two-dimensional visualization

Makoto Shozakai, Goshu Nagino, 2005, INTERSPEECH.

Design of ready-made acoustic model library by two-dimensional visualization of acoustic space

Makoto Shozakai, Goshu Nagino, 2004, INTERSPEECH.

Building an Effective Speech Corpus by Utilizing Statistical Multidimensional Scaling Method

Tomoki Toda, Kiyohiro Shikano, Hiroshi Saruwatari, 2008, IEICE Trans. Inf. Syst..

Analyzing reusability of speech corpus based on statistical multidimensional scaling method

Makoto Shozakai, Goshu Nagino, 2006, INTERSPEECH.