Sorry, you need to enable JavaScript to visit this website.

The detection of overlapping speech segments is of key importance in speech applications involving analysis of multi-party conversations. The detection problem is challenging because overlapping speech segments are typically captured as short speech utterances far-field microphone recordings. In this paper, we propose detection of overlap segments using a neural network architecture consisting of long-short term memory (LSTM) models. The neural network architecture learns the presence of overlap in speech by identifying the spectrotemporal structure of overlapping speech segments.

Motivated by applications such as ordinal embedding and collaborative ranking, we formulate homogeneous quadratic feasibility as an unconstrained, non-convex minimization problem. Our work aims to understand the landscape (local minimizers and global minimizers) of the non-convex objective, which corresponds to hinge losses arising from quadratic constraints. Under certain assumptions, we give necessary conditions for non-global, local minimizers of our objective and additionally show that in two dimensions, every local minimizer is a global minimizer.

This paper investigates semi-blind channel estimation in massive multiple-input multiple-output (MIMO) systems using different priors on data symbols. We derive two tractable expectation-maximization (EM) based channel estimation algorithms; one based on a Gaussian prior and the other one based on a Gaussian mixture model (GMM) for the unknown data symbols. The numerical results show that the semi-blind estimation schemes provide better channel estimates compared with the estimation based on training sequences only.

Recent works have proposed neural models for dialog act classification in spoken dialogs.
However, they have not explored the role and the usefulness of acoustic information.
We propose a neural model that processes both lexical and acoustic features for classification.
Our results on two benchmark datasets reveal that acoustic features are helpful in improving the overall accuracy.

Due to the grow of modern dataset size and the desire to harness computing power of multiple machines, there is a recent surge of interest in the design of distributed machine learning algorithms. However, distributed algorithms are sensitive to Byzantine attackers who can send falsified data to prevent the convergence of algorithms or lead the algorithms to converge to value of the attackers' choice. Our novel algorithm can deal with an arbitrary number of Byzantine attackers.

This work explores sequential Bayesian binary hypothesis testing in the social learning setup under expertise diversity. We consider a two-agent (say advisor-learner) sequential binary hypothesis test where the learner infers the hypothesis based on the decision of the advisor, a prior private signal, and individual belief. In addition, the agents have varying expertise, in terms of the noise variance in the private signal.