Audio–Driven Telemetry Inference for Formula 1
Re-construct F1 car telemetry and predict the team, circuit from onboard engine audio
Hey, I’m
Govinda Madhava
Audio Deep Learning | Digital Signal Processing | Music Information Retrieval ;)
EXPERIENCE
Research Collaborator @ Swara.Studio
Mar 2025 - Aug 2025
Santa Cruz, CA
- - Co-developed idtap, an open-source Python API for computational musicology, featuring a DSP-based auto-transcription system that converts recordings into trajectory-based notation through advanced pitch tracking and melodic segmentation.
- - Skills: Python, Real-time Music Transcription, Dataset Creation, Fast API
Audio Software Development Engineer @ Swar Systems
Jun 2024 - Jun 2025
Rolle, Switzerland
- - Designed an end-to-end ML pipeline delivering real-time, low-latency pitch shifting (±12 semitones) using Google Magenta DDSP and Granular Audio Synthesis, powering Tanpura Droid (1Mn+ downloads) and Swar Shala.
- - Applied time-frequency masking reducing audio bleeding in binaural datasets, improving Signal-to-Noise Ratio by 48%.
- - Optimized real-time user pitch tracking by improving Circular Buffer management & Dynamic Time Warping (DTW).
- - Skills: Python, C++, Machine Learning, Digital Signal Processing, Software Development, End-to-End Pipeline, Feature Processing
MusicTech Research Intern @ Digital Audio Processing Lab
Dec 2023 - Apr 2024
IIT Bombay, India
- - Curated a first-of-its-kind music dataset comprising 4 hrs of high quality audio, metadata & rendition-wise digitized notations.
- - Achieved 68% accuracy developing a Bi-LSTM architecture, the first auto transcription system for Indian classical vocal performances, converting audio signals to pitch contours and schematic notation.
- - Skills: Python, Machine Learning, Music Transcription, Dataset Creation
EDUCATION
Georgia Institute of Technology
Aug 2025 - Expected May 2027
Atlanta, USA
- MS, Music Technology | Music Informatics Group (Dr. Alexander Lerch)
PES University
Aug 2020 - Apr 2024
Bengaluru, India
- B.Tech, Computer Science & Engineering
FEATURED PROJECTS
Rhythm-Conditioned Music Generation with Meta MusicGen Model
Improved Meta's MusicGen audio generation model with fine-grained rhythmic control, outperforming larger pretrained encoders
Carnatic Music Visualiser
Understand Music by Visualising the Notes behind the Melody!
Pitch Pal
Developed a gamified interface using Unity and real-time DSP, letting users learn Western music sight-reading.
Bandish-to-Notation
Bi-LSTM model that automatically transcripts Indian Classical Music Vocal audio into Schematic Notation
RespirAI: Multi-modal Classification of Lung Diseases using Deep Learning
Multi-modal Deep Learning algorithm that diagnoses respiratory illnesses using Sthethoscope Audio and X-ray Images
I was initiated into music at a very early age by my mother Dr. Sandhya Shankar. Being gifted with musical talents, I started learning the Carnatic Violin from Vid. Lalgudi Rajalakshmi at the age of 5. I’m currently learning advanced violin lessons under the guidance of Vid Charulata Ramanujam. Since the past 18+ years, I have performed 200+ concerts as a violinist & vocalist at prestigious venues across India. I am also proud to be a part of social awareness and charity programs for children with special needs, saving indigenous cow breeds of India and Rotary outreach programs. I have also been part of the core music team in short-films and composing the anthem for our university cultural fest Atmatrisha with a footfall of 8,000+ students. I have been able to bring music to a larger audience by conducting music workshops, lecture demonstrations and jamming sessions at my University. Tutoring senior students, I employed innovative methods using my instrument to convey nuances and enhance the learning experience, which greatly benefited my students.