Improved Frame Level Features and SVM Supervectors Approach for the Recogniton of Emotional States from Speech: Application to categorical and dimensional states
This work addresses emotion recognition from speech, which is incremental as it builds on existing methods with frame-level features.
The paper tackled speech emotion recognition by evaluating frame-level feature extraction, achieving improved classification of emotional states using the Berlin emotional database.
The purpose of speech emotion recognition system is to classify speakers utterances into different emotional states such as disgust, boredom, sadness, neutral and happiness. Speech features that are commonly used in speech emotion recognition rely on global utterance level prosodic features. In our work, we evaluate the impact of frame level feature extraction. The speech samples are from Berlin emotional database and the features extracted from these utterances are energy, different variant of mel frequency cepstrum coefficients, velocity and acceleration features.