Publications

A statistical channel model for realistic simulation in VANET

Cardote A., Neves F., Sargento S., Steenkiste P.

IEEE Vehicular Networking Conference, VNC

2012

Conference Paper

Abstract:

Vehicular Ad-hoc NETwork (VANET) simulation is crucial for the development of new protocols and applications. Even though real-world experimentation is the de facto benchmarking solution for any of these, the first evaluations must be made through simulation, due to the ease of changing parameters and scenarios. In this work, we propose a statistical channel model for VANET simulation based on the observation of data from real-world experiments, obtained from an IEEE 802.11p / WAVE compliant testbed. We statistically characterize fading in VANET communication and propose a combination of models for Line-of-Sight (LoS) transmission. Simulations using the proposed model were compared with real-world experiment results and, furthermore, the model was validated against a set of measurements from an independent research group, fitting it with a high concordance level, thus proving to be effective and general.

A statistical phrase/accent model for intonation modeling

Anumanchipalli G.K., Oliveira L.C., Black A.W.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

2011

Conference Paper

Abstract:

This paper proposes a statistical phrase/accent model of voice fundamental frequency(F0) for speech synthesis. It presents an approach for automatic extraction and modeling of phrase and accent phenomena from F0 contours by taking into account their overall trends in the training data. An iterative optimization algorithm is described to extract these components, minimizing the reconstruction error of the F0 contour. This method of modeling local and global components of F0 separately is shown to be better than conventional F0 models used in Statistical Parametric Speech Synthesis (SPSS). Perceptual evaluations confirm that the proposed model is significantly better than baseline SPSS F0 models in 3 prosodically diverse tasks – read speech, radio broadcast speech and audio book speech.

A structured systems approach for optimal actuator-sensor placement in linear time-invariant systems

Pequito S., Kar S., Aguiar A.P.

Proceedings of the American Control Conference

2013

Conference Paper

Abstract:

In this paper we address the actuator/sensor allocation problem for linear time invariant (LTI) systems. Given the structure of an autonomous linear dynamical system, the goal is to design the structure of the input matrix (commonly denoted by B) such that the system is structurally controllable with the restriction that each input be dedicated, i.e., it can only control directly a single state variable. We provide a methodology to determine the minimum number of dedicated inputs required to ensure structural controllability, and characterize all (when not unique) possible configurations of the minimal input matrix B. Furthermore, we show that the proposed solution incurs polynomial complexity in the number of state variables. By duality, the solution methodology may be readily extended to the structural design of the corresponding minimal output matrix (commonly denoted by C) that ensures structural observability.

A style capturing approach to F0 transformation in voice conversion

Anumanchipalli G.K., Oliveira L.C., Black A.W.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

2013

Conference Paper

Abstract:

In this paper, we present a new approach to F0 transformation, that can capture aspects of speaking style. Instead of using the traditional 5ms frames as units in transformation, we propose a method that looks at longer phonological regions such as metrical feet. We automatically detect metrical feet in the source speech, and for each of source speaker’s feet, we find its phonological correspondence in target speech. We use a statistical phrase accent model to represent the F0 contour, where a 4-dimensional TILT representation is used for the F0 is parameterized over each feet region for the source and target speakers. This forms the parallel data that is the training data for our transformation. We transform the phrase component using simple z-score mapping. We use a joint density Gaussian mixture model to transform the accent contours. Our transformation method generates F0 contours that are significantly more correlated with the target speech than a baseline, frame-based method.

A theory for the connectivity discovered by routing protocols

Sobrinho J.L., Quelhas T.

IEEE/ACM Transactions on Networking

2012

Article

Abstract:

Route-vector protocols, such as the Border Gateway Protocol (BGP), have nodes elect and exchange routes in order to discover paths over which to send traffic. We ask the following: What is the minimum number of links whose failure prevents a route-vector protocol from finding such paths? The answer is not obvious because routing policies prohibit some paths from carrying traffic and because, on top of that, a route-vector protocol may hide paths the routing policies would allow. We develop an algebraic theory to address the above and related questions. In particular, we characterize a broad class of routing policies for which we can compute in polynomial time the minimum number of links whose failure leaves a route-vector protocol without a communication path from one given node to another. The theory is applied to a publicly available description of the Internet topology to quantify how much of its intrinsic connectivity is lost due to the traditional customer-provider, peer-peer routing policies and how much can be regained with simple alternative policies.

A Tutorial on Machine Learning for Interactive Pedagogical Systems

Melo F.S., Mascarenhas S., Paiva A.

International Journal of Serious Game

2018

Article

Abstract:

This paper provides a short introduction to the field of machine learning for interactive pedagogical systems. Departing from different examples encountered in interactive pedagogical systems—such as intelligent tutoring systems or serious games—we go over several representative families of methods in machine learning, introducing key concepts in this field. We discuss common challenges in machine learning and how current methods address such challenges. Conversely, by anchoring our presentation on actual interactive pedagogical systems, highlight how machine learning can benefit the development of such systems.

A unified algorithmic approach to distributed optimization

Mota J.F.C., Xavier J.M.F., Aguiar P.M.Q., Puschel M.

2013 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2013 - Proceedings

2013

Conference Paper

Abstract:

We address general optimization problems formulated on networks. Each node in the network has a function, and the goal is to find a vector x ∈ ℝ n that minimizes the sum of all the functions. We assume that each function depends on a set of components of x, not necessarily on all of them. This creates additional structure in the problem, which can be captured by the classification scheme we develop. This scheme not only to enables us to design an algorithm that solves very general distributed optimization problems, but also allows us to categorize prior algorithms and applications. Our general-purpose algorithm shows a performance superior to prior algorithms, including algorithms that are application-specific.

A Vertical PRF Architecture for Microblog Search

Martins F., Magalhães J., Callan J.

ICTIR '18 Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval

2018

Conference Paper

Abstract:

In microblog retrieval, query expansion can be essential to obtain good search results due to the short size of queries and posts. Since information in microblogs is highly dynamic, an up-to-date index coupled with pseudo-relevance feedback (PRF) with an external corpus has a higher chance of retrieving more relevant documents and improving ranking. In this paper, we focus on the research question:how can we reduce the query expansion computational cost while maintaining the same retrieval precision as standard PRF? Therefore, we propose to accelerate the query expansion step of pseudo-relevance feedback. The hypothesis is that using an expansion corpus organized into verticals for expanding the query, will lead to a more efficient query expansion process and improved retrieval effectiveness. Thus, the proposed query expansion method uses a distributed search architecture and resource selection algorithms to provide an efficient query expansion process. Experiments on the TREC Microblog datasets show that the proposed approach can match or outperform standard PRF in MAP and NDCG@30, with a computational cost that is three orders of magnitude lower.

Accent Group modeling for improved prosody in statistical parameteric speech synthesis

Anumanchipalli G.K., Oliveira L.C., Black A.W.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

2013

Conference Paper

Abstract:

This paper presents an `Accent Group’ based intonation model for statistical parametric speech synthesis. We propose an approach to automatically model phonetic realizations of fundamental frequency(F0) contours as a sequence of intonational events anchored to a group of syllables (an Accent Group). We train an accent grouping model specific to that of the speaker, using a stochastic context free grammar and contextual decision trees on the syllables. This model is used to `parse’ an unseen text into its constituent accent groups over each of which appropriate intonation is predicted. The performance of the model is shown objectively and subjectively on a variety of prosodically diverse tasks- read speech, news broadcast and audio books.