About me
Research Staff Member
Research lab: Watson Research Center (Yorktown)
Welcome to my home page! I am a research staff member at IBM’s T. J. Watson Research Center in Yorktown Heights, New York. I am also Senior Manager of the User Experience Technologies Department, a role that I took on recently. I have not yet hand a chance to update this page....so the information below is a bit dated. Previously I used to be Senior Manager, Speech Technologies Department which is part of the User Technologies Organization in IBM Research. I’ve been in the Speech area at IBM Research since March 1994 working on and leading efforts addressing core speech recognition problems. I was until recently an Associate Editor of the IEEE Transactions in Speech and Audio Processing and a member of the Speech Technical Committee of the IEEE Signal Processing Society.
Research activities in my group cover all aspects of speech recognition – signal processing, acoustic modeling, language modeling, search, semantic interpretation, dialog management, post-deployment analysis and tuning, speech self-service diagnostics and audio-visual processing – and occur in the context of several projects. The Telephony Speech Recognition project is aimed at developing algorithms for improving the accuracy & robustness of speech recognition in conversational telephony applications e.g., bank transactions, directory assistance, etc. This project has significant product impact by directly contributing algorithms and data files for WebSphere Voice Server and related voice technology offerings from IBM. The Embedded Speech Recognition project addresses low-resource, robust speech recognition. A significant outgrowth of this ongoing project is ViaVoice for Embedded Multiplatforms, IBM's state-of-the-art speech recognition offering for the PDA, smartphone & automotive environments. Key focus research areas are robust signal processing & efficient search strategies. The Conversational Multimodal Interaction project (managed by Roberto Sicconi) is aimed at developing the next generation dialog management strategies for both embedded (primarily automotive) and server environments by exploiting the latest concepts in UI design and leveraging multiple input and output modalities in a complementary fashion for an unparalleled end-user experience. The Audio-Visual Speech Recognition project addresses the use of visual information for enhanced speech detection and recognition in high-noise environments e.g., moving car.
Lately I have become very interested in research problems in the contact center area. Enterprise contact centers are going through major shifts due to some key business/technology trends: voice-data convergence and the emergence of IP contact centers, migration of contact centers from cost centers to profit centers, customer contact analytics driving business insights beyond contact centers to all functional areas in an enterprise, the growing popularity of hosted contact centers giving small and medium businesses a cost-effective approach to best-of-breed contact centers, offshore outsourcing of contact center operations and infrastructture etc. This opens up several technical challenges with enormous possibilities for research in the areas of multi-channel interaction, self-service, agent performance and customer contact analytics. IBM Research has a large initiative in this area - the Contact Center of the Future Initiative - and I'm a principal in this area at IBM Research.
Last updated 6 Jul 2007