Abstract
Automatic speech emotion recognition is a very necessary activity for effective human-computer interaction. This paper is motivated by using spectrograms as inputs to the hybrid deep convolutional LSTM for speech emotion recognition. In this study, we trained our proposed model using four convolutional layers for high-level feature extraction from input spectrograms, LSTM layer for accumulating long-term dependencies and finally two dense layers. Experimental results on the SAVEE database shows promising performance. Our proposed model is highly capable as it obtained an accuracy of 94.26%.
Highlights
We may ask ourselves why the emotional awareness by machines is even desirable [1]
We commenced our study by implementation of Convolution Neural Networks (CNNs)-Long Short-Term Memory (LSTM) architecture
Succeeding the performance graph are the screenshots of the spectrograms generated for each audio signal, the program results showing output and the emotion recognised for a particular audio input
Summary
We may ask ourselves why the emotional awareness by machines is even desirable [1]. Emotional awareness by machines can be used to provide tools to humans to make them more effective for example in gaming industry we can look or hear the gamer’s reaction and improve the game design by knowing the frustration point that is there in the game design. We can use emotion recognition to gauge the viewers’ reaction to the marketing materials and fine-tune the materials to achieve the desired effect [3], [4]. In all these applications, we need to build machines that are capable to perceive human emotional state. Emotion representation theory became the foundation for emotion recognition research by providing methods to give the various details of emotions so as to label the data with appropriate target and the machines can learn to predict the emotions [8]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering and Advanced Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
