Formula 1 Engine Audio Simulator
RNN-LSTM model to identify F1 Team/Engine, Track and Driver using onboard Engine Audio
Hey, I’m
Govinda Madhava B S
Every Noise has a Rhythm, every Chaos a Melody -- 1 Fourier Transform and the Music is revealed ;)
EXPERIENCE
Software Audio Developer @ Swar Systems
Jun 2024 - Present
Rolle, Switzerland / Remote
- - User Pitch Detection and Analysis Enhancement: Improved pitch detection & accuracy in PITCH PANE and PRACTICE PANE for real-time user audio analysis and evaluation.
- - Real-time Audio Pitch-Shifting: Used Phase Vocoder, Magenta DDSP and FFTW library tp enhance quality by retaining instrument timbre for natural glissando.
- - DholakAI: Reduce audio bleeding in binaural tabla dataset using time-frequency masking and implement pre-processing pipeline for AU/VST plugin.
- - Skills: C/C++, Python, DSP, Real-time Audio, Machine Learning, Music Transcription, App & Plugin Development
Audio Research Associate @ Pitch Innovations
Apr 2024 - Aug 2024
Chennai, India
- - Carnatic Raga Dataset: Created a dataset of violin audio samples showcasing various gamakas (ornamentations) with detailed notations, including pitch-bend data linked to specific swaras.
- - Real-Time Gamaka Prediction Model: Developed an ML model to predict user-input gamakas in real-time from the dataset, aimed for integration as an AU/VST plugin.
- - Skills: JUCE, Plugin Development, Real-time Audio, RAVE, Diffusion Models, CUBASE, Dataset creation
MusicTech Research Intern @ Digital Audio Processing Lab
Dec 2023 - Apr 2024
IIT Bombay, India
- - Created an audio dataset ~4 hours(6gb) comprising 2 Hindustani Music ragas, with metadata, detailed annotations, digitized notations and 3+ versions of the same bandish/piece rendered by multiple artists.
- - Developed a Bi-LSTM model to transcribe Indian classical vocal performances into schematic notation, enabling a comparison between different versions of the same classical piece, aiding Indian Music pedagogy and research.
- - Skills: Python, Music Transcription, Machine Learning, Dataset Creation, Indian Music Transcription & Pedagogy
EDUCATION
PES University
Aug 2020 - Apr 2024
Bengaluru, India
- B.Tech, Computer Science & Engineering
FEATURED PROJECTS
Bandish-to-Notation
Bi-LSTM model that automatically transcripts Indian Classical Music Vocal audio into Schematic Notation
Carnatic Music Visualiser
Understand Music by Visualising the Notes behind the Melody!
24notes
Listen to the 12 & 24-note Music Octaves Demo for a Tonic Frequency of your choice!!
Indian Raga Identifier
Classify Raga / Scale and Compare the performance of Machine Learning v/s Deep Learning algorithms
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.