Study on the Accent Independent Features for Speech Emotion Recognition

Abstract

Great progress have been made in speech recognition but we still have a long way to go to have a smooth human-computer interaction because the computer still finds it difficult to understand the emotional state of the speaker. This has introduced a brought into light a relatively recent research field, namely Speech Emotion Recognition. There are some implicit information about the emotions in every speech signal, which can be extracted through speech processing methods. There are many systems proposed in the literature to identify the emotional state through speech. Extraction of features from speech, Selecting a suitable feature set, designing a proper classifications method and preparing an proper dataset are the main points of designing a Speech Emotion Recognition (SER) systems. However despite significant progress in this area there still remains many things which are not well understood, specially, when attention was given to the cultural differences of people. Emotions Recognition in speech can vary from person to person based on their age, gender, language, accents and many other factors. To explore how much accents affect SER, we looked into how the feature varies for different accents in the domain of Speech Emotion Recognition. This paper focuses on the issue if Speech Emotion Recognition is Accent Independent or not. Study on different speech features, experiments on their extraction process and reduction techniques and experiments on selection of accent independent features are carried out. Which will be used to train a model and will lead us to a conclusion if SER depends on accents or not and which of the features of Speech help identify the emotions more accurately despite of the accent.