Speech Emotion Recognition (SER) systems have become indispensable tools in human-computer interaction, communication, and knowledge representation. Most SER systems are based on machine learning techniques and require large amounts of ground-truth data to be trained and achieve decent performance. This work presents a serious game and crowdsourcing techniques in the development and enhancement of SER models through the collection of annotating data. Serious games can contribute to and assist with this issue as a form of entertainment and informal education. In this direction, the online game "Raise Your Voice" was created, which enables the collection of recordings of emotionally charged speech in an accessible way, featuring a scheme of five distinct classes (anger, disgust, fear, happiness, and sadness). Using a web service architecture, speech emotion recognition is conducted during gameplay, helping players to evaluate and identify their effort. The main goal of the game is to attract users who will use this educational tool to express emotional speech through amusement and to create a mutually beneficial cooperative model between users and speech emotion recognition researchers.
(See document for exact affiliation information.)
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member Join the AES. If you need to check your member status, login to the Member Portal.
