Effective emotion recognition in movie audio tracks

Abstract

This paper addresses the problem of speech emotion recognition from movie audio tracks. The recently collected Acted Facial Expression in the Wild 5.0 database is used. The aim is to discriminate among angry, happy, and neutral. We extract a relatively small number of features, a subset of which is not commonly used for the emotion recognition task. Those features are fed as input to an ensemble classifier that combines random forests with support vector machines. An accuracy of 65.63% is reported, outperforming a baseline system that uses the K-nearest neighbor classifier and has an accuracy of 56.88%. To verify the suitability of the exploited features, the same ensemble classification schema is applied on the feature set similar those employed in Audio/Visual Emotion Challenge 2011. In the latter case, an accuracy of 61.25% is achieved using a large set of 1582 features, as opposed to just 86 features in our case that lead to a relative improvement of 7.15% in accuracy.

Real-time Emotion Recognition for Sales

“…Audio-based emotion recognition exploits features such as pitch, intensity, energy, and MFCCs (Mel-frequency cepstrum coefficients). Challenges in speech-based emotion recognition are that expression differs among subjects [9] and is directly influenced by age, culture, and externals factors such as the environment [10]. Video-based systems extract emotions from features such as facial expression, mouth, or eye shape [4].…”

Design & Development of Network Geo-Fencing Model for User Monitoring and it’s Alertness in a Security Applications

“…the frame size is size change 1ms effect noticeable changes in speech emotion recognition. [13] Focus on the emotion to differ between the angry, happy, and neutral. we extract the feature and subset which is not commonly used in the emotion recognition task.…”

Audio Analysis and Classification: A Review

“…The random forest has predicted the correct emotion and give the highest accuracy of 81.5%. Margarita Kotti [13] in 2017 The author introduces a method to recognize the emotion from movies and drama clips.focus on the emotion to differ between the angry, happy, and neutral. we extract the feature and subset which is not mostly used in the emotion recognition task.…”