Topic Switch Models for Dialogue Management in Virtual Humans

Zhu, Wenjue; Chowanda, Andry; Valstar, Michel

doi:10.1007/978-3-319-47665-0_43

Cited by 12 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea is to have a system capable of perceiving emotions from humans and reacting based on the perceived emotions (e.g., virtual humans [4]). By understanding the humans' emotions from the social conversation, the system provides more colourful interaction to humans [4,7,13,14]. Recognising emotions can be done with several features, such as: brainwave [15], heartbeat [16], voice prosody (e.g., the stress, rhythm and intonation of speech [17], facial expressions [18,19], and body gestures [20].…”

Section: Emotions Recognitionmentioning

confidence: 99%

Separable convolutional neural networks for facial expressions recognition

Chowanda

2021

J Big Data

Self Cite

View full text Add to dashboard Cite

Social interactions are important for us, humans, as social creatures. Emotions play an important part in social interactions. They usually express meanings along with the spoken utterances to the interlocutors. Automatic facial expressions recognition is one technique to automatically capture, recognise, and understand emotions from the interlocutor. Many techniques proposed to increase the accuracy of emotions recognition from facial cues. Architecture such as convolutional neural networks demonstrates promising results for emotions recognition. However, most of the current models of convolutional neural networks require an enormous computational power to train and process emotional recognition. This research aims to build compact networks with depthwise separable layers while also maintaining performance. Three datasets and three other similar architectures were used to be compared with the proposed architecture. The results show that the proposed architecture performed the best among the other architectures. It achieved up to 13% better accuracy and 6–71% smaller and more compact than the other architectures. The best testing accuracy achieved by the architecture was 99.4%.

show abstract

Section: Emotions Recognitionmentioning

confidence: 99%

Separable convolutional neural networks for facial expressions recognition

Chowanda

2021

J Big Data

Self Cite

View full text Add to dashboard Cite

show abstract

“…The idea is to have a system capable of perceiving emotions from humans and reacting based on the perceived emotions. By understanding the humans' emotions from the social conversation, the system provides more colourful interaction to humans [8,4,9,5]. Recognising emotions can be done with several features, such as: brainwave [10], heartbeat [11], voice prosody [12], facial expressions [13,14], and body gestures [15].…”

Section: Emotions Recognitionmentioning

confidence: 99%

Separable Convolutional Neural Networks For Facial Expressions Recognition

Chowanda

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Social interactions are important for us, human, as social creatures. Emotions play an important part in social interactions. They usually express meanings along with the spoken utterances to the interlocutors. Automatic facial expressions recognition is one technique to automatically capture, recognise, and understand emotions from the interlocutor. Many techniques proposed to increase the accuracy of emotions recognition from facial cues. Architecture such as convolutional neural networks demonstrates promising results for emotions recognition. However, most of the current models of convolutional neural networks require an enormous computational power to train and process emotional recognition. This research aims to build compact networks with depthwise separable layers while also maintaining performance. Three datasets and three other similar architectures were used to be compared to the proposed architecture. The results show that the proposed architecture performed the best among the other architectures. It achieved up to 13% better accuracy and 6-71% smaller and more compact than the other architectures. The best testing accuracy achieved by the architecture was 99.4%.

show abstract

“…Even though the TDT project was more about information retrieval than dialogue, the way of talking about topics as events can be useful for spontaneous casual conversation, because people talk about the news often when meeting. Zhu et al (2016) made a probabilistic topic switch model for an agent to match topics to user utterances and talk about related topics. The model took three things into account: topic frequency, concurrency and adjacency.…”

Section: Knowledge Basementioning

confidence: 99%

“…The model was trained on an annotated corpus, with a predefined list of topics. Zhu et al (2016) conducted an experiment and found that their topic switch model was more entertaining for users to interact with than without it. However, the granularity of topics was occasionally incorrect.…”

Section: Knowledge Basementioning

confidence: 99%

Personalized and personal conversations : designing agents who want to know you

Waterschoot

View full text Add to dashboard Cite

show abstract

Topic Switch Models for Dialogue Management in Virtual Humans

Cited by 12 publications

References 5 publications

Separable convolutional neural networks for facial expressions recognition

Separable convolutional neural networks for facial expressions recognition

Separable Convolutional Neural Networks For Facial Expressions Recognition

Personalized and personal conversations : designing agents who want to know you

Contact Info

Product

Resources

About