• Dr. M.K. Jayanthi Kannan
• Aditya Sharma
• Anushka Sizaria
• Elisabeth Varghese
• Divyanshu Chauhan, Prabhat Ranjan Srivastava

This project explores the application of machine learning techniques for the task of audio style transfer. The goal is to develop a model capable of converting an audio track from one genre to another, maintaining its underlying structure while adapting it to the musical characteristics of the target genre. By training on a diverse dataset of songs across multiple genres, the model learns to identify and manipulate key features such as rhythm, harmony, timbre, and instrumentation. This research aims to contribute to the developing body of work in the intersection of machine learning and audio processing, possibly offering new insights into genre-specific audio features and advancing the capabilities of AI in creative fields like music production. The outcomes of this project is to facilitate enhancements in music recommendation systems, automated music production tools, and creative applications in the entertainment industry.

Audio Processing, Genre transfer, Style transfer, Machine Learning, Feature Extraction.

"Morph My Tune", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.c358-c365, December-2024, Available :http://www.jetir.org/papers/JETIR2412240.pdf

"Morph My Tune", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppc358-c365, December-2024, Available at : http://www.jetir.org/papers/JETIR2412240.pdf