Artificial Emotional Intelligence in Socially Assistive Robots for Older Adults: A Pilot Study

This paper presents our recent research on integrating artificial emotional intelligence in a social robot (Ryan) and studies the robot's effectiveness in engaging older adults. Ryan is a socially assistive robot designed to provide companionship for older adults with depression and dementia through conversation. We used two versions of Ryan for our study, empathic and non-empathic. The empathic Ryan utilizes a multimodal emotion recognition algorithm and a multimodal emotion expression system. Using different input modalities for emotion, i.e. facial expression and speech sentiment, the empathic Ryan detects users' emotional state and utilizes an affective dialogue manager to generate a response. On the other hand, the non-empathic Ryan lacks facial expression and uses scripted dialogues that do not factor in the users' emotional state. We studied these two versions of Ryan with 10 older adults living in a senior care facility. The statistically significant improvement in the users' reported face-scale mood measurement indicates an overall positive effect from the interaction with both the empathic and non-empathic versions of Ryan. However, the number of spoken words measurement and the exit survey analysis suggest that the users perceive the empathic Ryan as more engaging and likable.

XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks

Although Capsule Networks show great abilities in defining the position relationship between features in deep neural networks for visual recognition tasks, they are computationally expensive and not suitable for running on mobile devices. The bottleneck is in the computational complexity of the Dynamic Routing mechanism used between capsules. On the other hand, neural networks such as XNOR-Net are fast and computationally efficient but have relatively low accuracy because of their information loss in the binarization process. This paper proposes a new class of Fully Connected (FC) Layers by xnorizing the linear projector outside or inside the Dynamic Routing within the CapsFC layer. Specifically, our proposed FC layers have two versions, XnODR (Xnorizing Linear Projector Outside Dynamic Routing) and XnIDR (Xnorizing Linear Projector Inside Dynamic Routing). To test their generalization, we insert them into MobileNet V2 and ResNet-50 separately. Experiments on three datasets, MNIST, CIFAR-10, MultiMNIST validate their effectiveness. Our experimental results demonstrate that both XnODR and XnIDR help networks to have high accuracy with lower FLOPs and fewer parameters (e.g., 95.32\% accuracy with 2.99M parameters and 311.22M FLOPs on CIFAR-10).

Facial Landmark Points Detection Using Knowledge Distillation-Based Neural Networks

Facial landmark detection is a vital step for numerous facial image analysis applications. Although some deep learning-based methods have achieved good performances in this task, they are often not suitable for running on mobile devices. Such methods rely on networks with many parameters, which makes the training and inference time-consuming. Training lightweight neural networks such as MobileNets are often challenging, and the models might have low accuracy. Inspired by knowledge distillation (KD), this paper presents a novel loss function to train a lightweight Student network (e.g., MobileNetV2) for facial landmark detection. We use two Teacher networks, a Tolerant-Teacher and a Tough-Teacher in conjunction with the Student network. The Tolerant-Teacher is trained using Soft-landmarks created by active shape models, while the Tough-Teacher is trained using the ground truth (aka Hard-landmarks) landmark points. To utilize the facial landmark points predicted by the Teacher networks, we define an Assistive Loss (ALoss) for each Teacher network. Moreover, we define a loss function called KD-Loss that utilizes the facial landmark points predicted by the two pre-trained Teacher networks (EfficientNet-b3) to guide the lightweight Student network towards predicting the Hard-landmarks. Our experimental results on three challenging facial datasets show that the proposed architecture will result in a better-trained Student network that can extract facial landmark points with high accuracy.

Oversampling Highly Imbalanced Indoor Positioning Data using Deep Generative Models

The location fingerprinting method, which typically utilizes supervised learning, has been widely adopted as a viable solution for the indoor positioning problem. Many indoor positioning datasets are imbalanced. Models trained on imbalanced datasets may exhibit poor performance on the minority class(es). This problem, also known as the "curse of imbalanced data," becomes more evident when class distributions are highly imbalanced. Motivated by the recent advances in deep generative modeling, this paper proposes using Variational Autoencoders and Conditional Variational Autoencoders as oversampling tools to produce class-balanced fingerprints. Experimental results based on Bluetooth Low Energy fingerprints demonstrate that the proposed method outperforms SMOTE and ADASYN in both minority class precision and overall precision. To promote reproducibility and foster new research efforts, we made all the codes associated with this work publicly available.

RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis

This paper introduces RyanSpeech, a new speech corpus for research on automated text-to-speech (TTS) systems. Publicly available TTS corpora are often noisy, recorded with multiple speakers, or lack quality male speech data. In order to meet the need for a high quality, publicly available male speech corpus within the field of speech recognition, we have designed and created RyanSpeech which contains textual materials from real-world conversational settings. These materials contain over 10 hours of a professional male voice actor's speech recorded at 44.1 kHz. This corpus's design and pipeline make RyanSpeech ideal for developing TTS systems in real-world applications. To provide a baseline for future research, protocols, and benchmarks, we trained 4 state-of-the-art speech models and a vocoder on RyanSpeech. The results show 3.36 in mean opinion scores (MOS) in our best model. We have made both the corpus and trained models for public use.

Topical Language Generation using Transformers

Large-scale transformer-based language models (LMs) demonstrate impressive capabilities in open text generation. However, controlling the generated text's properties such as the topic, style, and sentiment is challenging and often requires significant changes to the model architecture or retraining and fine-tuning the model on new supervised data. This paper presents a novel approach for Topical Language Generation (TLG) by combining a pre-trained LM with topic modeling information. We cast the problem using Bayesian probability formulation with topic probabilities as a prior, LM probabilities as the likelihood, and topical language generation probability as the posterior. In learning the model, we derive the topic probability distribution from the user-provided document's natural structure. Furthermore, we extend our model by introducing new parameters and functions to influence the quantity of the topical features presented in the generated text. This feature would allow us to easily control the topical properties of the generated text. Our experimental results demonstrate that our model outperforms the state-of-the-art results on coherency, diversity, and fluency while being faster in decoding.

BReG-NeXt: Facial Affect Computing Using Adaptive Residual Networks With Bounded Gradient

This paper introduces BReG-NeXt, a residual-based network architecture using a function wtih bounded derivative instead of a simple shortcut path (a.k.a. identity mapping) in the residual units for automatic recognition of facial expressions based on the categorical and dimensional models of affect. Compared to ResNet, our proposed adaptive complex mapping results in a shallower network with less numbers of training parameters and floating point operations per second (FLOPs). Adding trainable parameters to the bypass function further improves fitting and training the network and hence recognizing subtle facial expressions such as contempt with a higher accuracy. We conducted comprehensive experiments on the categorical and dimensional models of affect on the challenging in-the-wild databases of AffectNet, FER2013, and Affect-in-Wild. Our experimental results show that our adaptive complex mapping approach outperforms the original ResNet consisting of a simple identity mapping as well as other state-of-the-art methods for Facial Expression Recognition (FER). Various metrics are reported in both affect models to provide a comprehensive evaluation of our method. In the categorical model, BReG-NeXt-50 with only 3.1M training parameters and 15 MFLOPs, achieves 68.50% and 71.53% accuracy on AffectNet and FER2013 databases, respectively. In the dimensional model, BReG-NeXt achieves 0.2577 and 0.2882 RMSE value on AffectNet and Affect-in-Wild databases, respectively.

EmpTransfo: A Multi-head Transformer Architecture for Creating Empathetic Dialog Systems

Understanding emotions and responding accordingly is one of the biggest challenges of dialog systems. This paper presents EmpTransfo, a multi-head Transformer architecture for creating an empathetic dialog system. EmpTransfo utilizes state-of-the-art pre-trained models (e.g., OpenAI-GPT) for language generation, though models with different sizes can be used. We show that utilizing the history of emotions and other metadata can improve the quality of generated conversations by the dialog system. Our experimental results using a challenging language corpus show that the proposed approach outperforms other models in terms of Hit@1 and PPL (Perplexity).

Delivering Cognitive Behavioral Therapy Using A Conversational SocialRobot

Social robots are becoming an integrated part of our daily life due to their ability to provide companionship and entertainment. A subfield of robotics, Socially Assistive Robotics (SAR), is particularly suitable for expanding these benefits into the healthcare setting because of its unique ability to provide cognitive, social, and emotional support. This paper presents our recent research on developing SAR by evaluating the ability of a life-like conversational social robot, called Ryan, to administer internet-delivered cognitive behavioral therapy (iCBT) to older adults with depression. For Ryan to administer the therapy, we developed a dialogue-management system, called Program-R. Using an accredited CBT manual for the treatment of depression, we created seven hour-long iCBT dialogues and integrated them into Program-R using Artificial Intelligence Markup Language (AIML). To assess the effectiveness of Robot-based iCBT and users' likability of our approach, we conducted an HRI study with a cohort of elderly people with mild-to-moderate depression over a period of four weeks. Quantitative analyses of participant's spoken responses (e.g. word count and sentiment analysis), face-scale mood scores, and exit surveys, strongly support the notion robot-based iCBT is a viable alternative to traditional human-delivered therapy.

Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing

Residual-based neural networks have shown remarkable results in various visual recognition tasks including Facial Expression Recognition (FER). Despite the tremendous efforts have been made to improve the performance of FER systems using DNNs, existing methods are not generalizable enough for practical applications. This paper introduces Bounded Residual Gradient Networks (BReG-Net) for facial expression recognition, in which the shortcut connection between the input and the output of the ResNet module is replaced with a differentiable function with a bounded gradient. This configuration prevents the network from facing the vanishing or exploding gradient problem. We show that utilizing such non-linear units will result in shallower networks with better performance. Further, by using a weighted loss function which gives a higher priority to less represented categories, we can achieve an overall better recognition rate. The results of our experiments show that BReG-Nets outperform state-of-the-art methods on three publicly available facial databases in the wild, on both the categorical and dimensional models of affect.