In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our app...
Paris Smaragdis, Bhiksha Raj, Madhusudana V. S. Sh...
The paper addresses language model adaptation for automatic lecture transcription by fully exploiting presentation slide information used in the lecture. As the text in the presen...
Phoneme segmentation is a fundamental problem in many speech recognition and synthesis studies. Unsupervised phoneme segmentation assumes no knowledge on linguistic contents and a...
Self-stabilizing token circulation algorithms are not always adapted for dynamic networks. Random walks are well known to play a crucial role in the design of randomized algorithm...
Abstract—Authenticity and secrecy of broadcast message content is important in wireless sensor networks deployed for battlefield control, emergency response, and natural resourc...
Syed Taha Ali, Vijay Sivaraman, Ashay Dhamdhere, D...