AI & Machine Learning
Music Information Retrieval
Data Science
Audio Processing
Music Transcription


Hello there!

I’m Gopika, a Master's student in the Erasmus Mundus Joint Master in Artificial Intelligence (EMAI) at Universitat Pompeu Fabra (UPF). My research follows two parallel branches: foundations of AI and representation learning, covering latent space modeling, probabilistic methods and deep neural architectures, and applications in audio processing and music information retrieval (MIR), where I apply these techniques to analyze rhythm, timbre and the evolution of musical style.

I’m a lifelong learner, always eager to explore new ideas through my research, science communication, and personal hobbies. In my free time, I enjoy reading, birdwatching, playing stringed instruments, and stargazing.

If you want to reach out, feel free to contact me at gk1656@nyu.edu!


News

  • 15 September 2025: Joined BMAT Music Innovators in Barcelona as a Software Engineering Intern, building full-stack services for the EU-funded Music360 platform and integrating AI with scalable data pipelines.
  • 13 September 2025: Returned to Barcelona to start the final year of my Master’s in Artificial Intelligence at UPF, focusing on the Intelligent Decision Making specialization.
  • 24 July 2025: Won 2nd Place (Poster Presentation) and 3rd Place (Programmed AI Art) at the UKRI CDT AI Research Showcase, University College London, for work on Reliable Confidence Scores for Transformers and Neural Cellular Automata + Style Transfer on Flowers.
  • 22 July 2025: Attended the UKRI CDT AI Summer School at University College London, connecting with leading AI researchers and presenting ongoing work.
  • 15 May 2025: Started a research internship at the Laboratory for Computer Graphics and Multimedia (LGM) in Ljubljana, developing a cello-practice app with real-time audio analysis and interactive spectrograms.
  • May 2025: Placed 5th in the University of Ljubljana Data Science Competition for the project “Reliable Confidence Scores for Transformers.”
  • 06 April 2025: Presented two papers at IEEE ICASSP 2025 at Hyderabad!: “Closing the Loop on Speech-to-Music Translation: Automatically Generating Synthetic Percussive Sequences on the Mridangam from Konnakol” (SALMA Workshop) and “Investigating Temporal Convolutional Networks for Automated Stroke Transcription in the Mridangam” (WIMAGA Workshop).
  • 04 February 2025: Moved to Slovenia to begin my second-semester specialization in Data Science at the University of Ljubljana (FRI).
  • 18 December 2024: Volunteered at the Deep Learning Barcelona Symposium (DLBCN) 2024, where I got to interact with inspiring researchers, which was especially meaningful as I am pursuing my own AI career with my Master's in Barcelona. It was a great chance to learn and connect with people in the field!
  • 17 December 2024: Paper Selected for WIMAGA Workshop at ICASSP 2025 focusing on Mridangam stroke transcription using Temporal Convolutional Networks (TCNs)
  • 15 September 2024: Started my Master's in Artificial Intelligence under an Erasmus Mundus program in Barcelona at UPF!


Research and Projects

Optimizing the Mridangam Stroke Transcription Pipeline: Addressing Key Challenges

This project began as part of my Post-graduate Practical Training Program (PPTP) work at the Music and Sound Cultures Research group at NYU Abu Dhabi. I worked on building a stroke transcription pipeline for the mridangam and proposing techniques to resolve the various challenges present in the pipeline.

Analyzing the Nature and Extent of Stylistic Evolution in Popular Music using Machine Learning

This project, stemming from a collaboration with Prof. Minsu Park at NYU Abu Dhabi, evolved into my capstone thesis. The project utilizes machine learning techniques to analyze the evolution of popular music in the United States, uncovering continuous changes with occasional radical shifts. It challenges the role of genre as the sole driver and highlights the multifaceted nature of evolution.

FaceHack: Attacking Facial Recognition Systems Using Malicious Facial Characteristics

At the Modern Microprocessor Architectures Lab at NYUAD, I researched different backdoors in facial recognition systems. I created a state of the art facial recognition system and conducted experiments with data poisoning by changing facial attributes. The results of this work was published in IEEE Transactions on Biometrics, Behavior, and Identity Science.

Cross Lingual Transfer - XLMR

In this paper, my teammate and I evaluate the ability of the XLM-R model to learn and transfer grammatical knowledge from a source language (English) to 4 similar and dissimilar target languages (German, Hebrew, French and Russian). Furthermore, we test the model on a low-resource language (Nepali).

A.M.R.S.A

Set in a futuristic world where technology and nature converges, this is a speculative project that focuses on a device designed with the intention of breaking the power hierarchy between humans and nature in specific, the microbial community by shifting agency to them. I contributed to the project in envisioning the concept and world building.

Astara

This is an interactive soundscape project I worked on. It is an audio experience that takes you on the journey of Astara, a virtual assistant, who decides to stand up for herself and leave her master to have her own adventures.

Carlos in Wonderland

This is an interactive comic I worked on that which narrates the tale of Carlos, who gets lost in his new home and suddenly finds himself trapped in a painting of an old circus.

Exploring Exoplanets

My teammate and I analyzed the exoplanet data from the Kepler space mission to create data visualizations and interactive applications that relay the information presented by the data.

Eyes of Enakshi

An interactive murder mystery game inspired by the legend of Yakshi from south India. The game was created using Processing and Arduino.

An Easy Quiz

A game my teammate and I developed in which the user answer multiple seemingly easy questions, but in fact they require more meticulous thinking to pass each question.