18 citations
- Honda (Japan)JP4 papers
- Johns Hopkins UniversityUS2 papers
- Waseda UniversityJP2 papers
- École de Technologie SupérieureCA1 paper
- Kyoto UniversityJP1 paper
- Mitsubishi Electric Research Laboratories (United States)US1 paper
- Mitsubishi Electric (United States)US1 paper
- Polytechnique MontréalCA1 paper
- The University of OsakaJP1 paper
5 papers
A Framework for Building Closed-Domain Chat Dialogue Systems
Mikio Nakano, Kazunori Komatani
This paper presents HRIChat, a framework for developing closed-domain chat dialogue systems. Being able to engage in chat dialogues has been found effective for improving communica…
CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
Nelson Yalta, Shinji Watanabe, Takaaki Hori +2
Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recogn…
State-space analysis of an Ising model reveals contributions of pairwise interactions to sparseness, fluctuation, and stimulus coding of monkey V1 neurons
Jimmy Gaudreault, Hideaki Shimazaki
In this study, we analyzed the activity of monkey V1 neurons responding to grating stimuli of different orientations using inference methods for a time-dependent Ising model. The m…
Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
Nelson Yalta, Shinji Watanabe, Kazuhiro Nakadai +1
Synthesizing human's movements such as dancing is a flourishing research field which has several applications in computer graphics. Recent studies have demonstrated the advantages…
Neural Trajectory Analysis of Recurrent Neural Network In Handwriting Synthesis
Kristof B. Charbonneau, Osamu Shouno
Recurrent neural networks (RNNs) are capable of learning to generate highly realistic, online handwritings in a wide variety of styles from a given text sequence. Furthermore, the…