International Conference on Information and Knowledge Technology

Home / چهاردهمین کنفرانس بین المللی فناوری اطلاعات و دانش

Enhancing Supervised Learning in Speech Emotion Recognition through Unsupervised Representations

Authors :

Niloufar Faridani¹ Amirali Soltani Tehrani² Ramin Toosi³

1- دانشکده برق و کامپیوتر دانشگاه تهران 2- دانشکده برق و کامپیوتر دانشگاه تهران 3- دانشکده برق و کامپیوتر دانشگاه تهران

Keywords :

Speech Emotion Recognition،Self-supervised Learning،Convolutional Neural Network

Abstract :

Speech Emotion Recognition (SER) is pivotal in enhancing human-computer interaction by enabling a deeper understanding of emotional states across various applications, contributing to more empathetic and effective communication. This study proposes an innovative approach integrating self-supervised feature extraction with supervised classification for emotion recognition from small audio segments. In the preprocessing step, to eliminate the need to craft audio features, we employed a self-supervised feature extractor based on the Wav2Vec model to capture acoustic features from audio data. Then, the output feature maps of the preprocessing step are fed to a custom-designed Convolutional Neural Network (CNN)–-based model to perform emotion classification. Utilizing the ShEMO dataset as our testing ground, the proposed method surpasses two baseline methods, i.e., support vector machine classifier and transfer learning of a pre-trained CNN. Comparing the proposed method to the state-of-the-art techniques in the SER task indicates the superiority of the proposed method. Our findings underscore the pivotal role of deep unsupervised feature learning in elevating the landscape of SER, offering enhanced emotional comprehension in the realm of human-computer interactions.