no code implementations • 31 Jan 2024 • Xuecheng Niu, Akinori Ito, Takashi Nose
Therefore, we propose Scheduled Curiosity-Deep Dyna-Q (SC-DDQ), a curiosity-driven curriculum learning framework based on a state-of-the-art model-based reinforcement learning dialog model, Deep Dyna-Q (DDQ).
no code implementations • Interspeech 2020 • Yuya Chiba1, Takashi Nose1, Akinori Ito
One of the model’s weaknesses is that it cannot consider the statistics of speech features, which are known to be effective for speech emotion recognition.
no code implementations • LREC 2020 • Yoshihiro Yamazaki, Yuya Chiba, Takashi Nose, Akinori Ito
To facilitate research of such dialog systems, we are currently constructing a large-scale multimodal dialog corpus focusing on the relationship between speakers.
no code implementations • WS 2018 • Yuya Chiba, Takashi Nose, Taketo Kase, Mai Yamanaka, Akinori Ito
This paper explores the effect of emotional speech synthesis on a spoken dialogue system when the dialogue is non-task-oriented.
no code implementations • WS 2018 • Yukiko Kageyama, Yuya Chiba, Takashi Nose, Akinori Ito
In this paper, we conduct dialog experiments and show that controlling the form of system utterances can improve the users{'} impression.