Speech emotion recognition (SER) has gained significant attention due to its potential applications in areas such as human–computer interaction, sentiment analysis, and mental health monitoring. This paper surveys the use of decision tree classifiers as a method for SER, highlighting their interpretability and efficiency in handling emotional data. We explore different methods for feature extraction, specifically highlighting the Librosa libra, a popular tool for audio processing in Python. By comparing the performance of decision tree classifiers utilizing both traditional acoustic features, and those extracted through Librosa, we assess the impact of different feature sets on recognition accuracy. The results indicate that while decision trees provide a robust framework for SER, the integration of advanced feature extraction techniques from Librosa enhances classification performance. This paper concludes with insights into the challenges faced in SER and suggestions for future research directions, emphasizing the need for hybrid approaches that combine the strengths of both classical and modern methods.