Gossip-based information dissemination protocols are considered easy to deploy, scalable and resilient to network dynamics. They are also considered highly flexible, namely tunab...
We propose a new approach to adaptive system identification when the system model is sparse. The approach applies the ℓ1 relaxation, common in compressive sensing, to improve t...
This paper proposes a set of affine invariant features (AIFs) for sequence data. The proposed AIFs can be calculated directly from the sequence data, and their invariance to af...
A voice search system requires a speech interface that can correctly recognize spoken queries uttered by users. The recognition performance strongly relies on a robust language mo...
Xiao Li, Patrick Nguyen, Geoffrey Zweig, Dan Bohus
We measure the effects of a weak language model, estimated from as little as 100k words of text, on unsupervised acoustic model training and then explore the best method of using ...