Human Emotion Recognition from Speech in Audio Physical Features

Chatterjee, Akshay; Yasmin, Ghazaala

doi:10.1007/978-981-13-6772-4_70

Cited by 5 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, how does the explainer's cognitive process determine the degree and type of generalization required? While such a determination is itself a very difficult open research question being pursued by numerous researchers in fields such as culture modelling [53,54], user modelling [55][56][57], emotion recognition [58][59][60][61][62][63][64][65][66], and human computer interaction [67][68][69][70][71][72], we are interested in how the determination, once made, can be used to affect the explanation provided. We propose that this question implies that the cognitive and social processes form a cycle, as shown in Figure 2.…”

Section: Learning Processmentioning

confidence: 99%

“…This modeling of external actors is an active research field with substantial work already caried out. For instance, culture modelling [53,54], user modelling [55][56][57], emotion recognition [58][59][60][61][62][63][64][65][66], action recognition [136][137][138][139][140][141][142], pedestrian prediction [143][144][145][146][147][148] and human intention modelling [69][70][71][72] are just a few areas that could be considered as modelling external actors.…”

Section: Agentmentioning

confidence: 99%

See 1 more Smart Citation

Levels of explainable artificial intelligence for human-aligned conversational explanations

Dazeley

Vamplew

Foale

et al. 2021

Artificial Intelligence

View full text Add to dashboard Cite

Over the last few years there has been rapid research growth into eXplainable Artificial Intelligence (XAI) and the closely aligned Interpretable Machine Learning (IML). Drivers for this growth include recent legislative changes and increased investments by industry and governments, along with increased concern from the general public. People are affected by autonomous decisions every day and the public need to understand the decision-making process to accept the outcomes. However, the vast majority of the applications of XAI/IML are focused on providing low-level 'narrow' explanations of how an individual decision was reached based on a particular datum. While important, these explanations rarely provide insights into an agent's: beliefs and motivations; hypotheses of other (human, animal or AI) agents' intentions; interpretation of external cultural expectations; or, processes used to generate its own explanation. Yet all of these factors, we propose, are essential to providing the explanatory depth that people require to accept and trust the AI's decision-making. This paper aims to define levels of explanation and describe how they can be integrated to create a human-aligned conversational explanation system. In so doing, this paper will survey current approaches and discuss the integration of different technologies to achieve these levels with Broad eXplainable Artificial Intelligence (Broad-XAI), and thereby move towards high-level 'strong' explanations.

show abstract

Section: Learning Processmentioning

confidence: 99%

Section: Agentmentioning

confidence: 99%

Levels of explainable artificial intelligence for human-aligned conversational explanations

Dazeley

Vamplew

Foale

et al. 2021

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Emotions can be expressed verbally (through words and tone of voice) or nonverbally (facial expressions or body language), and they, therefore, can be recognized in many sources like images and videos [12], sounds [13], texts [14]. With respect to ED from voice/speech, images, videos, and other multimodal data, ED from text is more challenging and has been studied less than the other approaches [6].…”

Section: Introductionmentioning

confidence: 99%

ArmanEmo: A Persian Dataset for Text-based Emotion Detection

Mirzaee,

Peymanfard,

Moshtaghin

et al. 2024

Preprint

View full text Add to dashboard Cite

With the recent proliferation of open textual data on social media platforms, Emotion Detection (ED) from Text has received more attention over the past years. It has many applications, especially for businesses and online service providers, where emotion detection techniques can help them make informed commercial decisions by analyzing customers/users' feelings towards their products and services. In this study, we introduce ArmanEmo, a human-labeled emotion dataset of more than 7000 Persian sentences labeled for seven categories. The dataset has been collected from different resources, including Twitter, Instagram, and Digikala comments. Labels are based on Ekman's six basic emotions (Anger, Fear, Happiness, Hatred, Sadness, Wonder) and another category (Other) to consider any other emotion not included in Ekman's model. Along with the dataset, we have provided several baseline models for emotion classification focusing on the state-of-the-art transformer-based language models. Our best model achieves a macro-averaged F1 score of 75.39 percent across our test dataset. Moreover, we also conduct transfer learning experiments to compare our proposed dataset's generalization against other Persian emotion datasets. Results of these experiments suggest that our dataset has superior generalizability among the existing Persian emotion datasets. ArmanEmo is publicly available for non-commercial use at \url{https://github.com/Arman-Rayan-Sharif/arman-text-emotion}.

show abstract

Pattern analysis based acoustic signal processing: a survey of the state-of-art

Chaki

2020

Int J Speech Technol

View full text Add to dashboard Cite

Human Emotion Recognition from Speech in Audio Physical Features

Cited by 5 publications

References 10 publications

Levels of explainable artificial intelligence for human-aligned conversational explanations

Levels of explainable artificial intelligence for human-aligned conversational explanations

ArmanEmo: A Persian Dataset for Text-based Emotion Detection

Pattern analysis based acoustic signal processing: a survey of the state-of-art

Contact Info

Product

Resources

About