LSTM model achieves 99% accuracy in speech emotion recognition

Researchers have developed a novel speech emotion recognition system utilizing Mel-Frequency Cepstral Coefficients (MFCCs) for feature extraction and a Long Short-Term Memory (LSTM) neural network for classification. This approach demonstrated a 99% accuracy rate, outperforming a Support Vector Machine baseline which achieved 98% accuracy. The system shows promise for applications such as virtual assistants and mental health monitoring. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT This research advances speech emotion recognition accuracy, potentially improving human-computer interaction in virtual assistants and mental health applications.

RANK_REASON This is a research paper detailing a new model for speech emotion recognition.

Read on arXiv cs.AI →

• MFCC
• LSTM
• TESS
• SVM
• RBF kernel
• Kamorudeen Amuda

• paper
• other