INESC-ID

About: INESC-ID is a nonprofit organization based out in Lisbon, Portugal. It is known for research contribution in the topics: Field-programmable gate array & Control theory. The organization has 932 authors who have published 2618 publications receiving 37658 citations.

Comparison and combination of features in a hybrid HMM/MLP and a HMM/GMM speech recognition system

Abstract: Recently, the advantages of the spectral parameters obtained by frequency filtering (FF) of the logarithmic filter-bank energies (logFBEs) have been reported. These parameters, which are frequency derivatives of the logFBEs, lie in the frequency domain, and have shown good recognition performance with respect to the conventional mel-frequency cepstral coefficients (MFCCs) for hidden Markov models (HMM) based systems. In this paper, the FF features are first compared with the MFCCs and the relative spectral perceptual linear prediction (Rasta-PLP) features using both a hybrid HMM/MLP and a usual HMM/Gaussian mixture models (HMM/GMM) based recognition system, for both clean and noisy speech. Taking advantage of the ability of the hybrid system to deal with correlated features, the inclusion of both the frequency second-derivatives and the raw logFBEs as additional features is proposed and tested. Moreover, the robustness of these features in noisy conditions is enhanced by combining the FF technique with the Rasta temporal filtering approach. Finally, a study of the FF features in the framework of multistream processing is presented. The best recognition results for both clean and noisy speech are obtained from the multistream combination of the J-Rasta-PLP features and the FF features.

Papous: The Virtual Storyteller

Abstract: This paper describes the development of Papous, a Virtual Storyteller. Our ultimate goal is to obtain a synthetic character that tells stories in an expressive and believable way, just as a real human storyteller would do. In this paper we describe the first version of Papous, our virtual storyteller. Papous can be seen as a virtual narrator who reads a text enriched with control tags. These tags allow the storywriter to script the behaviour of Papous. There are four types of tags: behaviour tags, where a specific action or gesture is scripted; scene tags, that allows for Papous to change the scene where he tells the story; illumination tags, to allow a new illumination pattern of the scene; and emotion tags, to change the emotional state of Papous. The texts, enriched with these tags, are then processed by Papous' different modules, which contain an affective speech module and an affective body expression module. In this paper we will provide details of the speech, gestures and environment control actions taken by each of the modules of Papous architecture.

Automated Workload Characterization in Cloud-based Transactional Data Grids

Abstract: Cloud computing represents a cost-effective paradigm to deploy a wide class of large-scale distributed applications, for which the pay-per-use model combined with automatic resource provisioning promise to reduce the cost of dependability and scalability. However, a key challenge to be addressed to materialize the advantages promised by Cloud computing is the design of effective auto-scaling and self-tuning mechanisms capable of ensuring pre-determined QoS levels at minimum cost in face of changing workload conditions. This is one of the keys goals that are being pursued by the Cloud-TM project, a recent EU project that is developing a novel, self-optimizing transactional data platform for the cloud. In this paper we present the key design choices underlying the development of Cloud-TM's Workload Analyzer (WA), a crucial component of the Cloud-TM platform that is change of three key functionalities: aggregating, filtering and correlating the streams of statistical data gathered from the various nodes of the Cloud-TM platform, building detailed workload profiles of applications deployed on the Cloud-TM platform, characterizing their present and future demands in terms of both logical (i.e. data) and physical (e.g. hardware-related) resources, triggering alerts in presence of violations (or risks of future violations) of pre-determined SLAs.

Built-in aging monitoring for safety-critical applications

Abstract: Complex electronic systems for safety or mission-critical applications (automotive, space) must operate for many years in harsh environments. Reliability issues are worsening with device scaling down, while performance and quality requirements are increasing. One of the key reliability issues is to monitor long-term performance degradation due to aging in such harsh environments. For safe operation, or for preventive maintenance, it is desirable that such monitoring may be performed on chip. On-line built-in aging sensors (activated from time to time) can be an adequate solution for this problem. The purpose of this paper is to present a novel methodology for electronic systems aging monitoring, and to introduce a new architecture for an aging sensor. Aging monitoring is carried out by observing the degrading timing response of the digital system. The proposed solution takes into account power supply voltage and temperature variations and allows several levels of failure prediction. Simulation results are presented, that ascertain the usefulness of the proposed methodology.

Uncertain LDA: Including Observation Uncertainties in Discriminative Transforms

Abstract: Linear discriminant analysis (LDA) is a powerful technique in pattern recognition to reduce the dimensionality of data vectors. It maximizes discriminability by retaining only those directions that minimize the ratio of within-class and between-class variance. In this paper, using the same principles as for conventional LDA, we propose to employ uncertainties of the noisy or distorted input data in order to estimate maximally discriminant directions. We demonstrate the efficiency of the proposed uncertain LDA on two applications using state-of-the-art techniques. First, we experiment with an automatic speech recognition task, in which the uncertainty of observations is imposed by real-world additive noise. Next, we examine a full-scale speaker recognition system, considering the utterance duration as the source of uncertainty in authenticating a speaker. The experimental results show that when employing an appropriate uncertainty estimation algorithm, uncertain LDA outperforms its conventional LDA counterpart.