Speech Emotion Recognition Using Librosa

Author(s)	Yuvensiut Srie Susile, Jonathon Herawam
Country	Indonesia
Abstract	Speech emotion recognition (SER) has numerous uses in industries like psychology, entertainment, and healthcare and is a critical component of human-computer interaction. Deep learning techniques have advanced recently, and SER has drawn a lot of interest from the research community. Use of the librosa Python package for music and audio analysis, which offers a number of functions for feature extraction from voice signals, is one such method. In this study, we explain the key features and techniques for feature extraction and classification, and we examine the state-of-the-art methodologies for SER utilising librosa. We also point out the difficulties and restrictions associated with using librosa for SER and offer some potential paths for further study in this area. Overall, this paper sheds light on librosa's potential.
Keywords	Speech Emotion Recognition, Librosa, Kaggle, Spectrogram, Mel-Spectrogram, RAVDEES Dataset, MLP
Discipline	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 1, Issue 1, July-August 2023
Published On	2023-07-21
Cite This	Speech Emotion Recognition Using Librosa - Yuvensiut Srie Susile, Jonathon Herawam - AIJMR Volume 1, Issue 1, July-August 2023.

About AIJMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9328-605090	editor@aijmr.com

Advanced International Journal of Multidisciplinary Research