I am Soma Siddhartha, a mostly self-learnt ML researcher. I have research expertise in the fields of Speech and Vision, and building and taking products to production. Previously, worked as a founding engineer at gan.ai, where I led the development of various ML pipelines such as TTS, Voice Cloning and Lip Sync. Feel free to hit me up, if you are someone passionate about AI, want to break into this field or are interested in works that I have worked earlier. Let's learn from each other!