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

Abdollahi, Hojjat; Mahoor, Mohammad H.; Zandie, Rohola; Sewierski, Jarid; Qualls, Sara Honn

doi:10.1109/taffc.2022.3143803

Cited by 45 publications

(33 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As observed in Figs 4. (a), 4 (b) and 4 (c), the proposed ABMD model achieved commendably improved confusion ratio results.…”

supporting

confidence: 61%

“…Moreover, endeavors have continuously been made by researchers to ensure that emotion recognition is trans-formed from laboratory experiments to real-life situations [3]. This has seen emotional artificial intelligence being incorporated in social robots [4] that are used in a number of human-machine-interaction tasks. They are also used in senior citizens' home control systems [1] to monitor their emotional states, health and wellness.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Attention-Based Multi-Learning Approach for Speech Emotion Recognition With Dilated Convolution

2022

View full text Add to dashboard Cite

The success of deep learning in speech emotion recognition has led to its application in resource-constrained devices. It has been applied in human-to-machine interaction applications like social living assistance, authentication, health monitoring and alertness systems. In order to ensure a good user experience, robust, accurate and computationally efficient deep learning models are necessary. Recurrent neural networks (RNN) like long short-term memory (LSTM), gated recurrent units (GRU) and their variants that operate sequentially are often used to learn time series sequences of the signal, analyze longterm dependencies and the contexts of the utterances in the speech signal. However, due to their sequential operation, they encounter problems in convergence and sluggish training that uses a lot of memory resources and encounters the vanishing gradient problem. In addition, they do not consider spatial cues that may exist in the speech signal. Therefore, we propose an attention-based multi-learning model (ABMD) that uses residual dilated causal convolution (RDCC) blocks and dilated convolution (DC) layers with multi-head attention. The proposed ABMD model achieves comparable performance while taking global contextualized long-term dependencies between features in a parallel manner using a large receptive field with less increase in the number of parameters compared to the number of layers and considers spatial cues among the speech features. Spectral and voice quality features extracted from the raw speech signals are used as inputs. The proposed ABMD model obtained a recognition accuracy and F1 score of 93.75% and 92.50% on the SAVEE datasets, 85.89% and 85.34% on the RAVDESS datasets and 95.93% and 95.83% on the EMODB datasets. The model's robustness in terms of the confusion ratio of the individual discrete emotions especially happiness which is often confused with emotions that belong to the same dimensional plane with it also improved when validated on the same datasets.

show abstract

“…As observed in Figs 4. (a), 4 (b) and 4 (c), the proposed ABMD model achieved commendably improved confusion ratio results.…”

supporting

confidence: 61%

Section: Introductionmentioning

confidence: 99%

Attention-Based Multi-Learning Approach for Speech Emotion Recognition With Dilated Convolution

2022

View full text Add to dashboard Cite

show abstract

“…It's about being calm under pressure, helping others feel comfortable and understanding how your behaviour can affect your environment. While IQ aims to measure cognitive abilities, EI lies in our behaviour [23]. At first, EI seems abstract or haphazard, but our mind is a system, and we must treat it as such.…”

Section: What Is Emotional Intelligence (Ei)?mentioning

confidence: 99%

“…Once the appropriate emotion is identified, the machine interprets it and what it means in each case. As the database of emotions grows, algorithms become better at identifying the nuances of human communication [23].…”

Section: What Is Artificial Emotional Intelligence?mentioning

confidence: 99%

Project Managers Selection in the Construction Industry: Towards the Integration with Artificial Emotional Intelligence and Technology

Hanafi

Nawi

Rahim

et al. 2022

ARASET

View full text Add to dashboard Cite

Emotional intelligence (EI) comes almost automatically to humans when we respond instinctively. This basic level of intelligence tells us how to behave in certain scenarios. However, can this understanding be used with the help of technology in selecting efficient managers in the construction industry where the rate of increase in costs and delays in the construction project never ends and even increases? This conceptual paper proposes a study exploring the theory of artificial emotional intelligence in the construction industry to reduce the increase in cost and time overrun in the project using mixed-method research. The indicators of construction project management success were collected from the literature. The questionnaire was prepared for the second phase, and sample data will be collected from construction project managers nationwide through an online survey to form the new model. Finally, the data will be tested and analysed to see the relationship between construction project managers' EI and project success using artificial intelligence technology. Later, they will be validated with a group of certified project managers in an appropriate workshop. This study will conclude whether selecting an excellent project manager can be achieved with the help of artificial intelligence, characterised by emotional intelligence theory. The study will also verify if there is a significant correlation between the performance of construction project managers with elements in the EI theory by using artificial technology and the success of construction projects.

show abstract

“…1. Ryan Chatbot dataset: This is a specifically designed dataset developed for Ryan Robot [14,15] in different conversational settings. It contains more than 56,000 sentences covering a wide variety of topics, including television, sports, movies, music, science, food, museums, and history.…”

Section: Data Collectionmentioning

confidence: 99%

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

Zandie¹,

Mahoor²,

Madsen³

et al. 2021

Interspeech 2021

Self Cite

View full text Add to dashboard Cite

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 realworld 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.

show abstract

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

Cited by 45 publications

References 59 publications

Attention-Based Multi-Learning Approach for Speech Emotion Recognition With Dilated Convolution

Attention-Based Multi-Learning Approach for Speech Emotion Recognition With Dilated Convolution

Project Managers Selection in the Construction Industry: Towards the Integration with Artificial Emotional Intelligence and Technology

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

Contact Info

Product

Resources

About