Behind GoVivace Inc. are people who eat, breathe, and sleep human language technologies.
We develop speech recognition, speaker identification, voice authentication, speech synthesis, gender identification, language identification, and audio indexing software... get the drift?
Our services don’t stop at delivering standard solutions. We’re passionate about speech, remember? So we get you talking about your needs and we listen closely to understand exactly what these are. And if you think of it, who could comprehend you better than specialists in speech recognition?
Then, we tailor our offerings to exactly match your needs.In our business, this is called localization and customization of products. It’s a tedious (for us, you call the shots) process of creating a dictionary and grammar listing shoptalk words and phrases pertaining to your industry. The upshot of our efforts could be hands free operations for you and your staff, faster customer servicing, a leaner customer care team, better customer engagement from smarter offer-making, and more. Essentially, our work improves your work productivity.
We have worked with media companies, yellow pages service providers, security and information mining companies, telecom companies, and so on. Read on to know us better.
Nagendra Goel (CEO)Goel is passionate about speech processing technology, and would like to see speech recognition, synthesis and identification technologies being applied to greater effect in improving systems and their productivity across verticals.
Nagendra Goel has been CEO of GoVivace Inc. since 2009. He brings to the table the scientific expertise and sound understanding of customers’ needs required to manage and provide technical leadership to GoVivace’s engineering team. His strength is his love for detail and precision while not losing focus on the big picture. Prior to joining GoVivace, Goel co-founded and led the technology team of EnableDoc LLC, a company developing affordable, web-based electronic health records and practice management solutions for physicians. Over four years, he worked closely with clients to quickly adapt the web-based software to solve their day-to-day problems and deploy new technologies to introduce advanced features. He has also had productive stints with Apptek Inc. and Net2Voice Inc. where he was responsible for the development of speech recognition products. Previous experiences span product development for LSI Logic, the IBM T J Watson Research Center, Entropic Inc. and Telogy Networks. Goel is passionate about speech processing technology, and would like to see speech recognition, synthesis and identification technologies being applied to greater effect in improving systems and their productivity across verticals. Text processing, VoIP, SAAS and healthcare technologies are his other favorite technologies. He also digs Indian classical music, photography and gliding. He even holds a glider pilot license, albeit he hasn’t indulged this interest in recent years (too much work, you see). Goel holds a B.Tech degree in Electrical Engineering from Indian Institute Of Technology, Kanpur. He received his doctoral degree from The John Hopkins University, specializing in speech recognition and language technology.
Sanjeev Khudanpur, AdvisorKhudanpur’s career spans two decades of cutting edge research in human language technologies such as natural language processing, machine translation and automatic speech recognition, and in the statistical models of human language that the former technologies make heavy use of.
Sanjeev Khudanpur is an associate professor of Electrical and Computer Engineering at the Johns Hopkins Whiting School of Engineering. He also has a secondary appointment in the Computer Science department’s Human Language Technology Center of Excellence. Khudanpur has served on the faculty of the Johns Hopkins University since 1996. Khudanpur’s career spans two decades of cutting edge research in human language technologies such as natural language processing, machine translation and automatic speech recognition, and in the statistical models of human language that the former technologies make heavy use of. He has special interest in understanding the structure of such models and in estimating their parameters from data. Advancements in speech recognition, also in sensors and computational abilities will underlie the next generation of machines that Khudanpur foresees and is working towards creating. These machines will think for themselves, make decisions, and essentially operate themselves. Incidentally, he dreams big for himself too. He has set his sights on becoming a member of Congress, no less! Khudanpur holds a graduate (B.Tech.) degree in Electrical Engineering from the Indian Institute of Technology, Bombay. He pursued a doctorate in Electrical and Computer Engineering from the University of Maryland, studying Model Selection and Universal Data Compression, and was awarded the degree in 1997.
Daniel Povey, AdvisorAn indefatigable enthusiast of speech recognition technology, Povey has to his credit pioneering work on “discriminative training” of Hidden Markov Models for speech recognition, having developed many of the standard techniques.
Dan Povey was appointed Associate Research Scientist at the Center for Language and Speech Processing at the Johns Hopkins University in 2012. Povey researched speech recognition at Microsoft and IBM between 2003 and 2012. An indefatigable enthusiast of speech recognition technology, Povey has to his credit pioneering work on “discriminative training” of Hidden Markov Models for speech recognition, having developed many of the standard techniques. He is currently occupied with finding ways to represent generative models more compactly (such as the Subspace Gaussian Mixture Models approach), for purposes of more robust parameter estimation. Developing the open-source Kaldi speech recognition toolkit is another Povey passion, which has given him a thorough understanding and practice of speech recognition technology. Povey earned a doctorate from Cambridge University in 2003. He also acquired a BA in Natural Sciences Tripos from Cambridge.
 D.Povey,L. Burget et al.,"Subspace Gaussian Mixture Models For Speech Recognition", 2010, Submitted to: ICASSP
 L.Burget et al,"Multilingual Acoustic Modeling For Speech Recognition Based On Subspace Gaussian Mixture Models",2010,
Submitted to: ICASSP
 N.Goel et al.,"Approaches To Automatic Lexicon Learning With Limited Training Examples", 2010, submitted to: ICASSP.
 N.Kumar,"A Generalization Of Linear Discriminant Analysis In Maximum Likelihood Framework", 1996, submitted to:ISIP