Hey, I'm Venkatesh!
I am a computer vision researcher, software developer and a musician.
I am currently pursuing a Ph.D. with the Image Processing and Computer Vision Group (IPCV) and the Music Technology Group (MTG) at Universitat Pompeu Fabra (UPF) , Barcelona, under the supervision of Prof. Gloria Haro. My research primarily focuses on developing AI systems to perform intelligent tasks like source separation and synchronisation by exploiting the rich audio-visual correspondence between the audio-visual modalities. The possibility of working in the audio-visual domain opens doors to new applications like voice separation in multi-voice acappella music videos (multiple voices of the same singer could co-exist simultaneuously), where the audio-only approaches might not be suitable. My Ph.D. is supported by the INPhINIT "La Caixa" Marie Curie Fellowship Programme.
Interests
- Audio-visual Source Separation
- Audio-visual Synchronisation
- Speech, Singing Voice
- Deep Learning
- Music Information Retrieval
Education
-
Masters in Sound and Music Computing, 2018
Universitat Pompeu Fabra
-
Bachelors in Electrical and Electronics Engineering, 2015
National Institute of Technology Karnataka
