I am a professor of ECE, CS and Biomedical Engineering. I hold honorary professorships at the University of Cyprus and Universidad Nacional del Sur. I co-founded CLSP (with Moise Goldstein). My research interests are aimed at understanding the fundamental limits of computation/information processing under physical constraints such as energy, as well as brain inspired microsystems for sensory information processing. I am a writer of words, a builder of things, a thinker of thoughts, and a teacher of taughts.


I am an assistant professor in the CS department. My research interests are machine learning, speech recognition and statistical signal processing. I focus on dimensionality reduction and data representation, using machine learning techniques such as multiview learning, similarity-based learning, and deep learning, as well as methods from group theory, representation theory and harmonic analysis. Central to my research is the theory and application of stochastic approximation algorithms that can scale to big data.

I am a research scientist at the HLTCOE and an assistant research scientist with ECE, with my work spanning a number of disciplines. The commonalities are statistical pattern recognition, graph theory, data fusion, semi-supervised learning, and/or computational linguistics. I also tend to shy away from curated and cared-for datasets, instead preferring the wild-west of the real world. This may be in part due to my appreciation for the outdoors, especially water. I am a kayaker, rock climber, photographer, and SCUBA diver.

I am an assistant research professor of computer science and a research scientist at the Human Language Technology Center of Excellence (HLTCOE). I am also affiliated with the Machine Learning Group. I have a range of research interests in machine learning, natural language processing, speech, social media, intelligent user interfaces and health informatics. I use a variety of methods, including bayesian models, topic models, online learning, transfer learning, semi-supervised learning, and structured prediction.

I am an associate professor in the computer science department. My research focus is on formalizing linguistic structure and discovering it automatically. The first challenge is to fashion statistical models that are nuanced enough to capture good intuitions about linguistic structure. The second challenge is to develop efficient algorithms to learn these models from data. The third challenge is to unify our methodology and enable rapid experimentation: we are developing a high-level programming language, Dyna, that will let you specify your method abstractly and work out the implementation details for you.

I am an assistant professor in the ECE department. My research focuses on understanding how the brain processes and perceives sounds in noisy and complex acoustic environments, and translating this knowledge into robust sound and speech processing schemes. I am spearheading an effort to create a master's degree on speech and language technologies that will be administered out of CLSP.


John J. Godfrey is an adjunct professor at CLSP. His research focuses on acoustic phonetics for speaker characterization. Dr. Godfrey played a leading role in 2007 in establishing the Human Language Technology Center of Excellence (HLTCOE). He also coordinates the activities of a National Science Foundation project investigating the role of meaning representations in language understanding.

I am a Julian S.Smith Professor in Electrical Engineering, and the Director of the Center for Language and Speech Processing. The aim of my research is the design and development of systems that can reliably detect, identify, classify, and transmit information in speech. I am convinced that study and emulation of relevant aspects of biological systems, which are optimized by forces of nature to excel on these tasks, is the most effective way of approaching the challenge. I am also a faculty affiliate of the HLTCOE, an External Fellow of the International Computer Science Institute in Berkeley, California, and a Research Professor at the Brno University of Technology, Czech Republic.

I am a research scientist at the HLTCOE and an assistant research professor in the ECE department. My research explores various aspects of the speech recognition problem, with a focus on whole word acoustic modeling, sparse representations and models, and unsupervised/semi-supervised learning of words and speech sounds. Lately, I have been focused on developing zero resource speech technologies that require no transcribed speech for training and are thus agnostic to the language of application.

I am an associate professor with a primary appointment in the ECE department and a secondary appointment in CS. I am interested in the application of information theoretic methods to human language technologies such as automatic speech recognition and machine translation. All these technologies make heavy use of statistical models. I am interested in understanding the structure of such models and in estimating their parameters from data. I also organize the CLSP Summer Workshops to advance the greater research agenda of this field. I got both tenure and citizenship last year. Next up: congress.

I am a faculty member in the CS department. My work is currently focused on statistical machine translation (video), a subject on which I also wrote the textbook and maintain the website. More broadly, my interest is to make use of the vast amount of information that is available in digital form. I was one of the finalists for the 2013 European Inventor Award.

I am a assistant research professor in computer science and a research scientist at the HLTCOE. My research centers on statistical machine translation and its integration with speech and search technologies. Improvements to these systems depend on extensions and applications of machine learning, formal language theory, linguistics, and algorithms. I am interested in many problems in these fields.

I am a research scientist at the HLTCOE and in the CS department. My main research interests are machine translation and syntax in natural language processing; active research projects include language modeling, efficient decoding for machine translation, and text classification. I also maintain the Joshua decoder.

I am a research scientist with the CLSP. I finished my PhD in Cambridge University in 2003, and between 2003 and 2012 was doing speech recognition research at IBM and then Microsoft. I am mostly known for my work on "discriminative training" of Hidden Markov Models (HMMs) for speech recognition, having developed many of the standard techniques. My current interests include finding ways to represent generative models more compactly (e.g. the SGMM approach), for purposes of more robust parameter estimation, and also developing the open-source Kaldi speech recognition toolkit. Due to the Kaldi project I deal with most aspects of speech recognition technology.

I am an assistant professor in the computer science department. Broadly, my research interests include machine learning, probabilistic graphical models and computational healthcare optimization. I'm particularly interested in methods for semi-supervised/unsupervised learning, continually learning ML systems, Bayesian methods, and its applications in a variety of domains including user modeling, activity recognition, information extraction from text, and predictive models for medicine. I teach 'Machine Learning in Complex Domains' (or more informally titled, 'How to Become a Data Ninja') at Hopkins. I also run the Data Intensive Computing and Machine Learning weekly seminar. Beyond my research and teaching interests, I tend to enjoy all things high adrenaline.

I am a research scientist at the HLTCOE and an assistant research professor in the CS department. My research is in the areas of natural language processing (computational semantics, and social media analysis), and large scale data processing (streaming, and randomized algorithms).

I am a professor in the CS department. My research interests include natural language processing and spoken language systems, machine translation, information retrieval, very large text databases and machine learning. My research focuses on word sense disambiguation, minimally supervised induction algorithms in NLP, and multilingual natural language processing.

Back to Top