Year: 2007
Type: article
Abstract: In this report we summarize the state-of-the-art of speech emotion recognition from the signal \nprocessing point of view. On the bases of multi-corporal experiments with machine-learning classifiers, the \nobservation is made that existing approaches for supervised machine learning lead to database dependent \nclassifiers which can not be applied for multi-language speech emotion recognition without additional training \nbecause they discriminate the emotion classes following the used training language. As there are experimental \nresults showing that Humans can perform language independent categorisation, we made a parallel between \nmachine recognition and the cognitive process and tried to discover the sources of these divergent results. The \nanalysis suggests that the main difference is that the speech perception allows extraction of language \nindependent features although language dependent features are incorporated in all levels of the speech signal \nand play as a strong discriminative function in human perception. Based on several results in related domains, we \nhave suggested that in addition, the cognitive process of emotion-recognition is based on categorisation, assisted \nby some hierarchical structure of the emotional categories, existing in the cognitive space of all humans. We \npropose a strategy for developing language independent machine emotion recognition, related to the \nidentification of language independent speech features and the use of additional information from visual \n(expression) features.
Institutions: New Bulgarian University, Universidad Politécnica de Madrid
Language: English
Topic: Emotion and Mood Recognition
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W114469622