top of page


Researcher Sai Soumya

User-Centric AI-Based Multitrack Music Mixing Informed by Expert Practice

Music Mixing is a multi-faceted task that is technical, creative, and collaborative in nature. Once the audio tracks are recorded, these are handed over to a mixing engineer to create a cohesive mix that is well-balanced and representative of the artist's vision and identity. The task involves collaborative aspects like talking to the artist to understand their vision for the mix and exchanging demo mixes and reference songs, followed by engineering aspects where the engineer makes technical decisions to fix frequency masking, establish balance and panorama, and more. This is followed by more creative tasks that involve further transformations of audio tracks to get the desired sound. As a part of our PhD research, we have begun by understanding the intricacies of the process beyond the engineering aspect, so that we can build tools that are inspired and informed by the professional practice. To achieve this, we have so far conducted interviews and studies with professional and pro-am mixing engineers with significant experience and advanced skills in mixing to understand the workflow of mixing from the collaborative perspective. Our studies have shown that mixing engineers are more inclined towards technology that encourages assistance, collaboration, and easy integration into current workflows. We also found that mix engineers use reference songs and demo mixes as some of the directors to get a better understanding of the client's goals. Further, we are working on a deep learning-based model that uses the available expert knowledge about the engineering aspects of mixing informed by the collaborative standpoint to build a system that takes in stems and reference songs to predict parameters for the various audio effects in the mixing console for stems based on the mixing style of the reference song. This could help mix engineers create boilerplate mixes that they can further fine-tune to create the desired mix.

Screenshot 2023-11-20 at 15.33.11.png



Adoption of AI technology in music mixing workflows: An investigation

Soumya Sai Vanka, Maryam Safi, Jean-Baptiste Rolland, George Fazekas

AES Europe, May 2023



The role of communications and reference songs in the mixing process: Insights from professional mixing engineers

Soumya Sai Vanka, Maryam Safi, Jean-Baptiste Rolland, George Fazekas

Journal of Audio Engineering Society, Nov 2023



Deep learning for automatic mixing

Christian Steinmetz, Soumya Sai Vanka, Marco Martinez, Gary Bromham

ISMIR, Dec 2022



AI for multitrack mixing

Soumya Sai Vanka, Christian Steinmetz, Marco Martinez, Gary Bromham, Junghyun Koo, Brecht DeMan, Angeliki Mourgella

AES Convention NYC, Oct 2023


Music Production Style Transfer and Mix Similarity

Soumya Sai Vanka

DMRN, Dec 2021

Adoption of AI technology in music mixing workflows: An investigation

Soumya Sai Vanka Talks, May 2023

Previous Work: M.Sc. and B.Sc. (Physics)
I had the opportunity to conduct a few experiments in the field of sound and vibration during my undergraduate years when I was pursuing a Bachelor's in Physics [Hons.] Another time, I worked as a researcher (intern) at the Cryogenics department of IIT Kharagpur during the summer of 2019, where we devised a sensor to measure the Liq. Nitrogen levels in cylinders using superconductors. Click on the files to view the documentation of the experiments.

Development of an inductive based level sensor for LN2 level measurement in a tank

(May- June 2019, IIT Kharagpur, West Bengal, India)


A low-cost copper wire wound YBCO single crystal-based level sensor was devised and its performance was evaluated.


Fourier Analysis for woodwind instruments

(Oct 2017- April 2018, SSSIHL, Anantapur, Andhra Pradesh, India)

In this project, we analyzed the frequency spectrum of woodwinds, namely saxophone, flute, and clarinet to understand why they have distinctive timbre. We also studied the vibration modes of a clarinet in three different registers.


Study of the forced vibrations of a circular membrane

(Oct 2017- April 2018, SSSIHL, Anantapur, Andhra Pradesh, India)

Evidence of different modes of vibrations of the circular membrane with a change in frequency was explored and compared with the theoretical results given by Bessel’s function.

bottom of page