Yuichiro Yoshikawa

Seiya Mitsuno, Midori Ban, Hiroshi Ishiguro et al.

Social isolation among older adults has become a critical concern, as reduced opportunities for conversation and weakened family relationships negatively affect mental health. This study proposes a dialogue agent that supports older adults by fostering both a relationship with the agent and a relationship with their grandchild through sharing everyday information. The agent operates on a chatbot platform and engages in daily conversations with older adults and their grandchildren, exchanging information gathered from each party to enhance conversational engagement and social connection. We conducted a ten-day empirical experiment with 52 grandparent-grandchild pairs. The results suggest that older adults became more willing to interact with the proposed agent, which shared information about their grandchildren, and that the psychological connection between grandparents and grandchildren was strengthened. Furthermore, daily interactions with the agent were associated with reduced anxiety in both older adults and their grandchildren. These findings indicate that a dialogue agent that shares personal information can be an effective approach to supporting older adults by simultaneously offering conversational opportunities and promoting family connectedness. Overall, this study provides valuable insights into the design of dialogue agents that effectively address social isolation among older adults.

Changzeng Fu, Zelin Fu, Qi Zhang et al.

Depression is a widespread mental health issue affecting diverse age groups, with notable prevalence among college students and the elderly. However, existing datasets and detection methods primarily focus on young adults, neglecting the broader age spectrum and individual differences that influence depression manifestation. Current approaches often establish a direct mapping between multimodal data and depression indicators, failing to capture the complexity and diversity of depression across individuals. This challenge includes two tracks based on age-specific subsets: Track 1 uses the MPDD-Elderly dataset for detecting depression in older adults, and Track 2 uses the MPDD-Young dataset for detecting depression in younger participants. The Multimodal Personality-aware Depression Detection (MPDD) Challenge aims to address this gap by incorporating multimodal data alongside individual difference factors. We provide a baseline model that fuses audio and video modalities with individual difference information to detect depression manifestations in diverse populations. This challenge aims to promote the development of more personalized and accurate de pression detection methods, advancing mental health research and fostering inclusive detection systems. More details are available on the official challenge website: https://hacilab.github.io/MPDDChallenge.github.io.

Junya Nakanishi, Jun Baba, Yuichiro Yoshikawa et al.

This paper discusses the functional advantages of the Selection-Broadcast Cycle structure proposed by Global Workspace Theory (GWT), inspired by human consciousness, particularly focusing on its applicability to artificial intelligence and robotics in dynamic, real-time scenarios. While previous studies often examined the Selection and Broadcast processes independently, this research emphasizes their combined cyclic structure and the resulting benefits for real-time cognitive systems. Specifically, the paper identifies three primary benefits: Dynamic Thinking Adaptation, Experience-Based Adaptation, and Immediate Real-Time Adaptation. This work highlights GWT's potential as a cognitive architecture suitable for sophisticated decision-making and adaptive performance in unsupervised, dynamic environments. It suggests new directions for the development and implementation of robust, general-purpose AI and robotics systems capable of managing complex, real-world tasks.

Zhaojie Luo, Shoufeng Lin, Rui Liu et al.

Emotional voice conversion (VC) aims to convert a neutral voice to an emotional (e.g. happy) one while retaining the linguistic information and speaker identity. We note that the decoupling of emotional features from other speech information (such as speaker, content, etc.) is the key to achieving remarkable performance. Some recent attempts about speech representation decoupling on the neutral speech can not work well on the emotional speech, due to the more complex acoustic properties involved in the latter. To address this problem, here we propose a novel Source-Filter-based Emotional VC model (SFEVC) to achieve proper filtering of speaker-independent emotion features from both the timbre and pitch features. Our SFEVC model consists of multi-channel encoders, emotion separate encoders, and one decoder. Note that all encoder modules adopt a designed information bottlenecks auto-encoder. Additionally, to further improve the conversion quality for various emotions, a novel two-stage training strategy based on the 2D Valence-Arousal (VA) space was proposed. Experimental results show that the proposed SFEVC along with a two-stage training strategy outperforms all baselines and achieves the state-of-the-art performance in speaker-independent emotional VC with nonparallel data.

Shuyun Tang, Zhaojie Luo, Guoshun Nan et al.

Automatic emotion recognition (AER) based on enriched multimodal inputs, including text, speech, and visual clues, is crucial in the development of emotionally intelligent machines. Although complex modality relationships have been proven effective for AER, they are still largely underexplored because previous works predominantly relied on various fusion mechanisms with simply concatenated features to learn multimodal representations for emotion classification. This paper proposes a novel hierarchical fusion graph convolutional network (HFGCN) model that learns more informative multimodal representations by considering the modality dependencies during the feature fusion procedure. Specifically, the proposed model fuses multimodality inputs using a two-stage graph construction approach and encodes the modality dependencies into the conversation representation. We verified the interpretable capabilities of the proposed method by projecting the emotional states to a 2D valence-arousal (VA) subspace. Extensive experiments showed the effectiveness of our proposed model for more accurate AER, which yielded state-of-the-art results on two public datasets, IEMOCAP and MELD.

Yuki Okafuji, Yasunori Ozaki, Jun Baba et al.

Research currently being conducted on the use of robots as human labor support technology. In particular, the service industry needs to allocate more manpower, and it will be important for robots to support people. This study focuses on using a humanoid robot as a social service robot to convey information in a shopping mall, and the robot's behavioral concepts were analyzed. In order to convey the information, two processes must occur. Pedestrians must stop in front of the robot, and the robot must continue the engagement with them. For the purpose of this study, three types of autonomous behavioral concepts of the robot for the general use were analyzed and compared in these processes in the experiment: active, passive-negative, and passive-positive concepts. After interactions were attempted with 65,000+ pedestrians, this study revealed that the passive-negative concept can make pedestrians stop more and stay longer. In order to evaluate the effectiveness of the robot in a real environment, the comparative results between three behaviors and human advertisers revealed that (1) the results of the active and passive-positive concepts of the robot are comparable to those of the humans, and (2) the performance of the passive-negative concept is higher than that of all participants. These findings demonstrate that the performance of robots is comparable to that of humans in providing information tasks in a limited environment; therefore, it is expected that service robots as a labor support technology will be able to perform well in the real world.

Yuki Tamaru, Yasunori Ozaki, Yuki Okafuji et al.

For a humanoid robot to make eye contact and initiate communication with a person, it is necessary to estimate the person's head position. However, eye contact becomes difficult due to the mechanical delay of the robot when the person is moving. Owing to these issues, it is important to conduct a head-position prediction to mitigate the effect of the delay in the robot motion. Based on the fact that humans turn their heads before changing direction while walking, we hypothesized that the accuracy of three-dimensional (3D) head-position prediction from a first-person view can be improved by considering the head pose. We compared our method with a conventional Kalman filter-based approach, and found our method to be more accurate. The experiment results show that considering the head pose helps improve the accuracy of 3D head-position prediction.

Changzeng Fu, Chaoran Liu, Carlos Toshinori Ishi et al.

Text categorization is the task of assigning labels to documents written in a natural language, and it has numerous real-world applications including sentiment analysis as well as traditional topic assignment tasks. In this paper, we propose 5 different configurations for the semantic matrix-based memory neural network with end-to-end learning manner and evaluate our proposed method on two corpora of news articles (AG news, Sogou news). The best performance of our proposed method outperforms the baseline VDCNN models on the text classification task and gives a faster speed for learning semantics. Moreover, we also evaluate our model on small scale datasets. The results show that our proposed method can still achieve better results in comparison to VDCNN on the small scale dataset. This paper is to appear in the Proceedings of the 2020 IEEE 14th International Conference on Semantic Computing (ICSC 2020), San Diego, California, 2020.

Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa et al.

For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human-robot interaction experiences gathered in the real uncontrolled environments. The results indicate that the robot not only acquired human-like social skills but also took more human-like decisions, on a test dataset, than a robot which received direct rewards for the task achievement.

Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa et al.

For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social interaction skills after 14 days of interacting with people in an uncontrolled real world. Each and every day during the 14 days, the system gathered robot interaction experiences with people through a hit-and-trial method and then trained the MDARQN on these experiences using end-to-end reinforcement learning approach. The results of interaction based learning indicate that the robot has learned to respond to complex human behaviors in a perceivable and socially acceptable manner.

Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa et al.

For robots to coexist with humans in a social world like ours, it is crucial that they possess human-like social interaction skills. Programming a robot to possess such skills is a challenging task. In this paper, we propose a Multimodal Deep Q-Network (MDQN) to enable a robot to learn human-like interaction skills through a trial and error method. This paper aims to develop a robot that gathers data during its interaction with a human and learns human interaction behaviour from the high-dimensional sensory information using end-to-end reinforcement learning. This paper demonstrates that the robot was able to learn basic interaction skills successfully, after 14 days of interacting with people.