Open AccessSemi-supervised Learning Techniques for Speech Emotion Recognition
Author(s) -
K. R. Remya,
B. S. Shajee Mohan,
K. V. Ahammed Muneer
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1921/1/012029
Subject(s) - computer science , emotion recognition , speech recognition , semi supervised learning , artificial intelligence , supervised learning , metric (unit) , speech processing , graph , machine learning , natural language processing , pattern recognition (psychology) , artificial neural network , economics , operations management , theoretical computer science
The core objective of this paper is to explore semi-supervised learning methods for recognizing emotions contained in speech. Semi-supervised learning techniques are used when the availability of labeled examples are sparse. There are different methods that are used in the semi-supervised settings. These techniques include generative model, graph based methods, metric based methods etc., The speech emotion data is considered for this experiment. Speech signal contains emotion specific data also. Emotion dependent features are extracted from the speech. This paper aim to enhance some existing techniques for semi-supervised learning that are used for speech emotion recognition.