Empathic and Empathetic Systematic Review to Standardize the Development of Reliable and Sustainable Empathic Systems

Daher, Karl; Saad, Dahlia; Mugellini, Elena; Lalanne, Denis; Khaled, Omar Abou

doi:10.3390/s22083046

Cited by 5 publications

(6 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can see that almost all examples with positive emotions -e1 and e4 (high valence)are in the major scale and examples with negative emotions -e2 and e3 (low valence) -in the minor scale. The entire set of MIDI files labeled with the emotions along with the proposed system code and generated music examples can be found at the following link 1 .…”

Section: B Example Annotation With Emotion Labelsmentioning

confidence: 99%

“…It consists of two parallel branches of analysis, which at the end are connected with the Concatenate layer. Each branch contains two sequential convolutional layers (Conv2D) with an increasing number of filters (64, 128) and with special kernel size (1,12) for analyzing 12 octave semitones, and kernel size (4, 1) for analyzing the next time steps.…”

Section: B Implementationmentioning

confidence: 99%

“…Fig. 8 presents CNN layers of the decoder, which, similarly to the encoder, also consists of two parallel branches, sequentially transposed convolution layers (Conv2DTranspose); the number of convolutional filters decreases (64, 128) and the kernel sizes are analogous to those in the encoder (1,12) and (4, 1). In standard convolutional layers, kernels in the form of a square are most often used, e.g.…”

Section: B Implementationmentioning

confidence: 99%

“…Due to the fact that the dimensions of the analyzed images have a certain meaning (pitch, time step), it was decided to modify the kernel size. Kernel (1,12) analyzed the whole octave (12 semitones) and kernel (4, 1) analyzed four time steps equal to one quarter note. The ReLU function in the decoder and the LeakyReLU function in the encoder were used as the activation functions in the layers.…”

Section: B Implementationmentioning

confidence: 99%

“…In this, it is not enough to simply recognize the current human emotion, even if a multimodal approach is used. For proper, comprehensive communication, an empathetic response is also necessary [1]. Such a non-verbal response can be, depending on the mood or situation, generated music.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Generating Polyphonic Symbolic Emotional Music in the Style of Bach Using Convolutional Conditional Variational Autoencoder

Grekow

2023

IEEE Access

View full text Add to dashboard Cite

In times of increasing human-machine interaction, the implementation of emotional intelligence in machines should not only recognize and track emotions during human interaction, but also respond with appropriate emotional content. Machines should be able to react and respond to human emotions. Music generation with a specific emotion is part of this task. This article presents the process of building a system generating polyphonic music content of a specified emotion using a conditional variational autoencoder and convolutional layers. The process of preparing a database of training examples with compositions by Johann Sebastian Bach, selecting and conducting transformations of musical examples was described. Annotation with emotion labels was done by music experts with a university music education. The four emotion labelshappy, angry, sad, relaxed -corresponding to the four quadrants of Russell's model were used. The process of coding symbolic music examples into a time-pitch matrix representation, but also the structure of the built variational autoencoder, was described. Experiments on the implementation of different convolutional layers intended for visual analysis of the representation of music examples were presented. The generated emotional music files were evaluated using metrics and expert opinions.

show abstract

Section: B Example Annotation With Emotion Labelsmentioning

confidence: 99%

Section: B Implementationmentioning

confidence: 99%

Section: B Implementationmentioning

confidence: 99%

Section: B Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Generating Polyphonic Symbolic Emotional Music in the Style of Bach Using Convolutional Conditional Variational Autoencoder

Grekow

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

Towards Contextualizing Embodiment of Intelligent Systems

Moharana,

Washington,

Carrington

et al. 2024

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Measuring perceived empathy in dialogue systems

Concannon

Tomalin

2023

AI & Soc

View full text Add to dashboard Cite

Dialogue systems, from Virtual Personal Assistants such as Siri, Cortana, and Alexa to state-of-the-art systems such as BlenderBot3 and ChatGPT, are already widely available, used in a variety of applications, and are increasingly part of many people’s lives. However, the task of enabling them to use empathetic language more convincingly is still an emerging research topic. Such systems generally make use of complex neural networks to learn the patterns of typical human language use, and the interactions in which the systems participate are usually mediated either via interactive text-based or speech-based interfaces. In human–human interaction, empathy has been shown to promote prosocial behaviour and improve interaction. In the context of dialogue systems, to advance the understanding of how perceptions of empathy affect interactions, it is necessary to bring greater clarity to how empathy is measured and assessed. Assessing the way dialogue systems create perceptions of empathy brings together a range of technological, psychological, and ethical considerations that merit greater scrutiny than they have received so far. However, there is currently no widely accepted evaluation method for determining the degree of empathy that any given system possesses (or, at least, appears to possess). Currently, different research teams use a variety of automated metrics, alongside different forms of subjective human assessment such as questionnaires, self-assessment measures and narrative engagement scales. This diversity of evaluation practice means that, given two DSs, it is usually impossible to determine which of them conveys the greater degree of empathy in its dialogic exchanges with human users. Acknowledging this problem, the present article provides an overview of how empathy is measured in human–human interactions and considers some of the ways it is currently measured in human–DS interactions. Finally, it introduces a novel third-person analytical framework, called the Empathy Scale for Human–Computer Communication (ESHCC), to support greater uniformity in how perceived empathy is measured during interactions with state-of-the-art DSs.

show abstract

Empathic and Empathetic Systematic Review to Standardize the Development of Reliable and Sustainable Empathic Systems

Cited by 5 publications

References 101 publications

Generating Polyphonic Symbolic Emotional Music in the Style of Bach Using Convolutional Conditional Variational Autoencoder

Generating Polyphonic Symbolic Emotional Music in the Style of Bach Using Convolutional Conditional Variational Autoencoder

Towards Contextualizing Embodiment of Intelligent Systems

Measuring perceived empathy in dialogue systems

Contact Info

Product

Resources

About