Author Login IJIRT Partner Network (IPN) Login

A Comparative Analysis of Machine Learning and Deep Learning Techniques for Speech Emotion Recognition

  • Unique Paper ID: 163640
  • Volume: 10
  • Issue: 11
  • PageNo: 1928-1937
  • Abstract:
  • This review paper explores Speech Emotion Recognition (SER) techniques, comparing traditional Machine Learning (ML) and Deep Learning (DL) approaches. We analyze the strengths and weaknesses of each approach, particularly regarding feature engineering and model complexity. The paper discusses how ML methods rely on handcrafted features like Mel-Frequency Cepstral Coefficients (MFCCs) for emotion classification using algorithms like Support Vector Machines (SVMs) or k-Nearest Neighbors (kNN). Conversely, Deep Learning techniques, particularly Long Short-Term Memory (LSTM) networks, have emerged as powerful tools for SER due to their ability to automatically learn features directly from raw audio data. We examine the trade-offs between interpretability of ML models and the data-driven feature learning capabilities of Deep Learning. Additionally, the paper explores challenges faced by both approaches, including data availability and domain adaptation. Finally, we discuss the potential applications of SER technology across various domains and highlight promising future directions in this evolving field.
Download article email to a friend

Cite This Article

  • ISSN: 2349-6002
  • Volume: 10
  • Issue: 11
  • PageNo: 1928-1937

A Comparative Analysis of Machine Learning and Deep Learning Techniques for Speech Emotion Recognition

Related Articles

Impact Factor
8.01 (Year 2024)
UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Archive

View More

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry