About

I am currently a principal machine learning research engineer at Bose Research (2017-present). Previously I was a researcher at the CompMusic Project, Music Technology Group (MTG), Universitat Pompeu Fabra, Barcelona, Spain. I received my Ph.D from Georgetown University (USA) with a focus on computational linguistics and natural language processing.

My research interest is machine learning for NLP and audio. Previously I worked on speech prosody, coreference resolution, audio time-series and text data mining, with applications in Music Information Retrieval (MIR) and computational musicology. I also contributed to NLP and Digital Humanities open source software such as ANNIS and GitDOX. Currently at Bose, my team focuses on deep learning for audio applications for our next generation audio AI products, including audio understanding, source separation, and generative audio.