Fusion of Acoustic and Linguistic Information using Supervised Autoencoder for Improved Emotion Recognition

Vlasenko, Bogdan; Prasad, RaviShankar; Magimai.-Doss, Mathew

doi:10.1145/3475957.3484448

Cited by 6 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More popular method, however, is bag-of-words with subsequent tf-idf weighting [12], which is based on broad language traits. In line with previous studies, we later use tf-idf characteristics as our baseline and machine learning models [13].…”

Section: Related Workmentioning

confidence: 99%

Linguistic Based Emotion Detection from Live Social Media Data Classification Using Metaheuristic Deep Learning Techniques

Mubeen¹,

Kulkarni²,

Tanpoco³

et al. 2022

Int. j. commun. netw. inf. secur.

View full text Add to dashboard Cite

A crucial area of research that can reveal numerous useful insights is emotional recognition. Several visible ways, including speech, gestures, written material, and facial expressions, can be used to portray emotion. Natural language processing (NLP) and DL concepts are utilised in the content-based categorization problem that is at the core of emotion recognition in text documents.This research propose novel technique in linguistic based emotion detection by social media using metaheuristic deep learning architectures. Here the input has been collected as live social media data and processed for noise removal, smoothening and dimensionality reduction. Processed data has been extracted and classified using metaheuristic swarm regressive adversarial kernel component analysis. Experimental analysis has been carried out in terms of precision, accuracy, recall, F-1 score, RMSE and MAP for various social media dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Linguistic Based Emotion Detection from Live Social Media Data Classification Using Metaheuristic Deep Learning Techniques

Mubeen¹,

Kulkarni²,

Tanpoco³

et al. 2022

Int. j. commun. netw. inf. secur.

View full text Add to dashboard Cite

show abstract

“…Using the openSMILE toolkit [25] 5 , we extract 88 extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) features [24] which have shown their suitability for sentiment analysis and SER tasks [8,59]. For each sub-challenge, we apply the standard configuration and extract features with a window size of two seconds, and a hop size of 500 ms.…”

Section: Egemapsmentioning

confidence: 99%

The MuSe 2022 Multimodal Sentiment Analysis Challenge

Christ

Amiriparian

Baird³

et al. 2022

Proceedings of the 3rd International on Multimodal Sentiment Analysis Workshop and Challenge

View full text Add to dashboard Cite

nnnnnnn feature sets. As a competitive baseline system, a Gated Recurrent Unit (GRU)-Recurrent Neural Network (RNN) is employed. On the respective sub-challenges' test datasets, it achieves a mean (across three continuous intensity targets) Pearson's Correlation Coefficient of .4727 for MuSe-Mimic, an Area Under the Curve (AUC) value of .8310 for MuSe-Humour and Concordance Correlation Coefficient (CCC) values of .7482 for arousal and .7827 for valence in the MuSe-Personalisation sub-challenge. CCS CONCEPTS• Computing methodologies → Neural networks; Artificial intelligence; Computer vision; Natural language processing.

show abstract

“…SMILE toolkit [29] to extract 88 dimensional extended Geneva Minimalistic Acoustic Parameter Set ( G MAPS) features [28], which have shown to be robust for sentiment analysis and SER tasks [10,50,62,66]. We employ the standard configuration for each sub-challenge and extract features using a window size of 2000 ms and a hop size of 500 ms.…”

Section: G Maps We Utilize Thementioning

confidence: 99%

MuSe 2022 Challenge

Amiriparian

Christ

König

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

The Multimodal Sentiment Analysis Challenge (MuSe) 2024 addresses two contemporary multimodal affect and sentiment analysis problems: In the Social Perception Sub-Challenge (M S P), participants will predict 16 different social attributes of individuals such as assertiveness, dominance, likability, and sincerity based on the provided audio-visual data. The Cross-Cultural Humor Detection Sub-Challenge (M S H) dataset expands upon the Passau Spontaneous Football Coach Humor (P SFCH) dataset, focusing on the detection of spontaneous humor in a cross-lingual and cross-cultural setting. The main objective of MuSe 2024 is to unite a broad audience from various research domains, including multimodal sentiment analysis, audio-visual affective computing, continuous signal processing, and natural language processing. By fostering collaboration and exchange among experts in these fields, the MuSe 2024 endeavors to advance the understanding and application of sentiment analysis and affective computing across multiple modalities. This baseline paper provides details on each subchallenge

show abstract

Fusion of Acoustic and Linguistic Information using Supervised Autoencoder for Improved Emotion Recognition

Cited by 6 publications

References 23 publications

Linguistic Based Emotion Detection from Live Social Media Data Classification Using Metaheuristic Deep Learning Techniques

Linguistic Based Emotion Detection from Live Social Media Data Classification Using Metaheuristic Deep Learning Techniques

The MuSe 2022 Multimodal Sentiment Analysis Challenge

MuSe 2022 Challenge

Contact Info

Product

Resources

About