Deepu Vijayasenan

LipiTk: a generic toolkit for online handwriting recognition

This paper describes Lipi Toolkit (LipiTk) - a generic toolkit whose aim is to facilitate development of online handwriting recognition engines for new scripts, and simplify integration of the resulting engines into real-world application contexts. The toolkit provides robust implementations of tools, algorithms, scripts and sample code necessary to support the activities of handwriting data collection and annotation, training and evaluation of recognizers, packaging of engines and their integration into pen-based applications. The toolkit is designed to be extended with new tools and algorithms to meet the requirements of specific scripts and applications. The toolkit attempts to satisfy the requirements of a diverse set of users, such as researchers, commercial technology providers, do-it-yourself enthusiasts and application developers. In this paper we describe the first version of the toolkit which focuses on isolated online handwritten shape and character recognition.

Estimating multiple physical parameters from speech data

In this work, we explore prediction of different physical parameters from speech data. We aim to predict shoulder size and waist size of people from speech data in addition to the conventional height and weight parameters. A data-set with this information is created from 207 volunteers. A bag of words representation based on log magnitude spectrum is used as features. A support vector regression predicts the physical parameters from the bag of the words representation. The system is able to achieve a root mean square error of 6.6 cm for height estimation, 2.6cm for shoulder size, 7.1cm for waist size and 8.9 kg for weight estimation. The results of height estimation is on par with state of the art results.