About me

I am a PhD student in the Computer Science department and the Center for Language and Speech Processing at the Johns Hopkins University in Baltimore, Maryland. Daniel Povey and Sanjeev Khudanpur co-advise my research, which focuses on discriminatively trained representations for speaker recognition, spoken language recognition, and speaker diarization. I also collaborate with Daniel Garcia-Romero, Gregory Sell and Alan McCree of the Human Language Technology Center of Excellence. I am a co-inventor of x-vectors, the first state-of-the-art neural embedding for text-independent speaker recognition. As a contributor to the Kaldi toolkit, I develop and maintain the speaker recognition and diarization systems. My industry experience in speech processing includes internships at Amazon Alexa and ICF International as well as consulting with Spoken Communications. I am a recipient of the 2013 NSF Graduate Research Fellowship, which partially supports my research at JHU. Before coming to Baltimore, I received a BS in Computer Science from Portland State University.