Faculty of Engineering, Tokushima University, Tokushima, Japan.
PLoS One. 2019 May 2;14(5):e0215216. doi: 10.1371/journal.pone.0215216. eCollection 2019.
In this paper, we propose an Emotional Trigger System to impart an automatic emotion expression ability within the humanoid robot REN-XIN, in which the Emotional Trigger is an emotion classification model trained from our proposed Word Mover's Distance(WMD) based algorithm. Due to the long time delay of the WMD-based Emotional Trigger System, we propose an enhanced Emotional Trigger System to enable a smooth interaction with the robot in which the Emotional Trigger is replaced by a conventional convolution neural network and a long short term memory network (CNN_LSTM)-based deep neural network. In our experiments, the CNN_LSTM based model only need 10 milliseconds or less to finish the classification without a decrease in accuracy, while the WMD-based model needed approximately 6-8 seconds to give a result. In this paper, the experiments are conducted based on the same sub-data sets of the Chinese emotional corpus(Ren_CECps) used in former WMD experiments: one comprises 50% data for training and 50% for testing(1v1 experiment), and the other comprises 80% data for training and 20% for testing(4v1 experiment). The experiments are conducted using WMD, CNN_LSTM, CNN and LSTM. The results show that CNN_LSTM obtains the best F1 score (0.35) in the 1v1 experiment and almost the same accuracy of F1 scores (0.366 vs 0.367) achieved by WMD in the 4v1 experiment. Finally, we present demonstration videos with the same scenario to show the performance of robot control driven by CNN_LSTM-based Emotional Trigger System and WMD-based Emotional Trigger System. To improve the comparison, total manual-control performance is also recorded.
在本文中，我们提出了一种情感触发系统，为类人机器人 REN-XIN 赋予自动情感表达能力，其中情感触发是一种基于我们提出的词动距离（WMD）算法训练的情感分类模型。由于基于 WMD 的情感触发系统的时间延迟较长，我们提出了一种增强的情感触发系统，使机器人能够进行流畅的交互，其中情感触发由传统卷积神经网络和基于长短期记忆网络（CNN_LSTM）的深度神经网络代替。在我们的实验中，基于 CNN_LSTM 的模型只需 10 毫秒或更短的时间即可完成分类，而不会降低准确性，而基于 WMD 的模型则需要大约 6-8 秒才能得出结果。在本文中，实验基于与之前 WMD 实验中使用的相同的中文情感语料库（Ren_CECps）子集进行：一个包含 50%的数据用于训练，50%的数据用于测试（1v1 实验），另一个包含 80%的数据用于训练，20%的数据用于测试（4v1 实验）。实验使用 WMD、CNN_LSTM、CNN 和 LSTM 进行。实验结果表明，在 1v1 实验中，CNN_LSTM 获得了最佳 F1 分数（0.35），在 4v1 实验中，WMD 的 F1 分数（0.366 对 0.367）几乎相同。最后，我们展示了相同场景的演示视频，展示了基于 CNN_LSTM 的情感触发系统和基于 WMD 的情感触发系统驱动的机器人控制性能。为了提高可比性，还记录了总手动控制性能。
