Exploring Jukebox: A Novel Audio Representation for Music Genre Identification in MIR
Authors:
- 3 May 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
For Music Information Retrieval (MIR) downstream tasks, the most common audio representation is time-frequency-based, such as Mel spectrograms. In order to identify musical genres, this study explores the possibilities of a new form of audio representation—one of the most usual MIR downstream tasks. Therefore, to discretely encoding music using deep vector quantization; a novel audio representation was created for the innovative generative music model i.e. Jukebox. The effectiveness of Jukebox’s audio representation is compared to Mel spectrograms using a dataset that is almost equivalent to State-of-the-Art (SOTA) and an almost same transformer design. The results of this study imply that, at least when the transformers are pretrained using a very modest dataset of 20k tracks, Jukebox’s audio representation is not superior to Mel spectrograms. This could be explained by the fact that Jukebox’s audio representation does not sufficiently take into account the peculiarities of human hearing perception. On the other hand, Mel spectrograms are specifically created with the human auditory sense in mind.Keywords
This publication has 11 references indexed in Scilit:
- Enhancing the predictive capability of a mathematical model for pseudomonas aeruginosa through artificial neural networksInternational Journal of Information Technology, 2024
- Enhancing End-to-End Multi-Task Dialogue Systems: A Study on Intrinsic Motivation Reinforcement Learning Algorithms for Improved Training and Adaptability2024
- Advancing Audio Fingerprinting Accuracy with AI and ML: Addressing Background Noise and Distortion Challenges2024
- Spectroformer: Multi-Domain Query Cascaded Transformer Network For Underwater Image Enhancement2024
- Stock Price Prediction Using Artificial Intelligence Based on LSTM–Deep Learning Model2023
- Predicting the Infection Level of COVID-19 Virus Using Normal Distribution-Based Approximation Model and PSO2023
- An analysis of the robustness of UAV agriculture field coverage using multi-agent reinforcement learningInternational Journal of Information Technology, 2023
- Using Machine Learning to Quantify the Multimedia Risk Due to FuzzingMultimedia Tools and Applications, 2021
- MusiCoder: A Universal Music-Acoustic Encoder Based on Transformer2021
- Definition of the Opus Audio Codec2012