Análise de Desempenho e Recomendação para Soluções IVR

Mestrado em Engenharia Informática, Área de Especialização em Tecnologias do Conhecimento e da Decisão

Adaptive modeling and high quality spectral estimation for speech enhancement

In this work an adaptive modeling and spectral estimation scheme based on a dual Discrete Kalman Filtering (DKF) is proposed for speech enhancement. Both speech and noise signals are modeled by an autoregressive structure which provides an underlying time frame dependency and improves time-frequency resolution. The model parameters are arranged to obtain a combined state-space model and are also used to calculate instantaneous power spectral density estimates. The speech enhancement is performed by a dual discrete Kalman filter that simultaneously gives estimates for the models and the signals. This approach is particularly useful as a pre-processing module for parametric based speech recognition systems that rely on spectral time dependent models. The system performance has been evaluated by a set of human listeners and by spectral distances. In both cases the use of this pre-processing module has led to improved results.

Speech as the basic interface for assistive technology

Speech interfaces for Assistive Technologies are not common and are usually replaced by others. The market they are targeting is not considered attractive and speech technologies are still not well spread. Industry still thinks they present some performance risks, especially Speech Recognition systems. As speech is the most elemental and natural way for communication, it has strong potential for enhancing inclusion and quality of life for broader groups of users with special needs, such as people with cerebral palsy and elderly staying at their homes. This work is a position paper in which the authors argue for the need to make speech become the basic interface in assistive technologies. Among the main arguments, we can state: speech is the easiest way to interact with machines; there is a growing market for embedded speech in assistive technologies, since the number of disabled and elderly people is expanding; speech technology is already mature to be used but needs adaptation to people with special needs; there is still a lot of R&D to be done in this area, especially when thinking about the Portuguese market. The main challenges are presented and future directions are proposed.

Multi-criteria optimization manipulator trajectory planning

In the last twenty years genetic algorithms (GAs) were applied in a plethora of fields such as: control, system identification, robotics, planning and scheduling, image processing, and pattern and speech recognition (Bäck et al., 1997). In robotics the problems of trajectory planning, collision avoidance and manipulator structure design considering a single criteria has been solved using several techniques (Alander, 2003). Most engineering applications require the optimization of several criteria simultaneously. Often the problems are complex, include discrete and continuous variables and there is no prior knowledge about the search space. These kind of problems are very more complex, since they consider multiple design criteria simultaneously within the optimization procedure. This is known as a multi-criteria (or multiobjective) optimization, that has been addressed successfully through GAs (Deb, 2001). The overall aim of multi-criteria evolutionary algorithms is to achieve a set of non-dominated optimal solutions known as Pareto front. At the end of the optimization procedure, instead of a single optimal (or near optimal) solution, the decision maker can select a solution from the Pareto front. Some of the key issues in multi-criteria GAs are: i) the number of objectives, ii) to obtain a Pareto front as wide as possible and iii) to achieve a Pareto front uniformly spread. Indeed, multi-objective techniques using GAs have been increasing in relevance as a research area. In 1989, Goldberg suggested the use of a GA to solve multi-objective problems and since then other researchers have been developing new methods, such as the multi-objective genetic algorithm (MOGA) (Fonseca & Fleming, 1995), the non-dominated sorted genetic algorithm (NSGA) (Deb, 2001), and the niched Pareto genetic algorithm (NPGA) (Horn et al., 1994), among several other variants (Coello, 1998). In this work the trajectory planning problem considers: i) robots with 2 and 3 degrees of freedom (dof ), ii) the inclusion of obstacles in the workspace and iii) up to five criteria that are used to qualify the evolving trajectory, namely the: joint traveling distance, joint velocity, end effector / Cartesian distance, end effector / Cartesian velocity and energy involved. These criteria are used to minimize the joint and end effector traveled distance, trajectory ripple and energy required by the manipulator to reach at destination point. Bearing this ideas in mind, the paper addresses the planning of robot trajectories, meaning the development of an algorithm to find a continuous motion that takes the manipulator from a given starting configuration up to a desired end position without colliding with any obstacle in the workspace. The chapter is organized as follows. Section 2 describes the trajectory planning and several approaches proposed in the literature. Section 3 formulates the problem, namely the representation adopted to solve the trajectory planning and the objectives considered in the optimization. Section 4 studies the algorithm convergence. Section 5 studies a 2R manipulator (i.e., a robot with two rotational joints/links) when the optimization trajectory considers two and five objectives. Sections 6 and 7 show the results for the 3R redundant manipulator with five goals and for other complementary experiments are described, respectively. Finally, section 8 draws the main conclusions.

Anotação colaborativa de conteúdos utilizando jogos com propósito

Com o crescimento da informação disponível na Web, arquivos pessoais e profissionais, protagonizado tanto pelo aumento da capacidade de armazenamento de dados, como pelo aumento exponencial da capacidade de processamento dos computadores, e do fácil acesso a essa mesma informação, um enorme fluxo de produção e distribuição de conteúdos audiovisuais foi gerado. No entanto, e apesar de existirem mecanismos para a indexação desses conteúdos com o objectivo de permitir a pesquisa e acesso aos mesmos, estes apresentam normalmente uma grande complexidade algorítmica ou exigem a contratação de pessoal altamente qualificado, para a verificação e categorização dos conteúdos. Nesta dissertação pretende-se estudar soluções de anotação colaborativa de conteúdos e desenvolver uma ferramenta que facilite a anotação de um arquivo de conteúdos audiovisuais. A abordagem implementada é baseada no conceito dos “Jogos com Propósito” (GWAP – Game With a Purpose) e permite que os utilizadores criem tags (metadatos na forma de palavras-chave) de forma a atribuir um significado a um objecto a ser categorizado. Assim, e como primeiro objectivo, foi desenvolvido um jogo com o propósito não só de entretenimento, mas também que permita a criação de anotações audiovisuais perante os vídeos que são apresentados ao jogador e, que desta forma, se melhore a indexação e categorização dos mesmos. A aplicação desenvolvida permite ainda a visualização dos conteúdos e metadatos categorizados, e com o objectivo de criação de mais um elemento informativo, permite a inserção de um like num determinado instante de tempo do vídeo. A grande vantagem da aplicação desenvolvida reside no facto de adicionar anotações a pontos específicos do vídeo, mais concretamente aos seus instantes de tempo. Trata-se de uma funcionalidade nova, não disponível em outras aplicações de anotação colaborativa de conteúdos audiovisuais. Com isto, o acesso aos conteúdos será bastante mais eficaz pois será possível aceder, por pesquisa, a pontos específicos no interior de um vídeo.

Automatic syllabification for danish text-to-speech systems

In this paper, a rule-based automatic syllabifier for Danish is described using the Maximal Onset Principle. Prior success rates of rule-based methods applied to Portuguese and Catalan syllabification modules were on the basis of this work. The system was implemented and tested using a very small set of rules. The results gave rise to 96.9% and 98.7% of word accuracy rate, contrary to our initial expectations, being Danish a language with a complex syllabic structure and thus difficult to be rule-driven. Comparison with data-driven syllabification system using artificial neural networks showed a higher accuracy rate of the former system.

Plataforma de gestão de incidentes

Mestrado em Engenharia Electrotécnica e de Computadores. Área de Especialização de Telecomunicações.

Modelling and segmentation of the vocal tract during speech production by using deformable models in magnetic resonance images

The first and second authors would like to thank the support of the PhD grants with references SFRH/BD/28817/2006 and SFRH/PROTEC/49517/2009, respectively, from Fundação para a Ciência e Tecnol ogia (FCT). This work was partially done in the scope of the project “Methodologies to Analyze Organs from Complex Medical Images – Applications to Fema le Pelvic Cavity”, wi th reference PTDC/EEA- CRO/103320/2008, financially supported by FCT.

Differences in Mismatch Negativity (MMN) response to Pure-tone and Speech sounds in normal subjects: an additional explanation

The relation of automatic auditory discrimination, measured with MMN, with the type of stimuli has not been well established in the literature, despite its importance as an electrophysiological measure of central sound representation. In this study, MMN response was elicited by pure-tone and speech binaurally passive auditory oddball paradigm in a group of 8 normal young adult subjects at the same intensity level (75 dB SPL). The frequency difference in pure-tone oddball was 100 Hz (standard = 1 000 Hz; deviant = 1 100 Hz; same duration = 100 ms), in speech oddball (standard /ba/; deviant /pa/; same duration = 175 ms) the Portuguese phonemes are both plosive bi-labial in order to maintain a narrow frequency band. Differences were found across electrode location between speech and pure-tone stimuli. Larger MMN amplitude, duration and higher latency to speech were verified compared to pure-tone in Cz and Fz as well as significance differences in latency and amplitude between mastoids. Results suggest that speech may be processed differently than non-speech; also it may occur in a later stage due to overlapping processes since more neural resources are required to speech processing.

On the development of an automatic voice pleasantness classification and intensity estimation system

In the last few years, the number of systems and devices that use voice based interaction has grown significantly. For a continued use of these systems, the interface must be reliable and pleasant in order to provide an optimal user experience. However there are currently very few studies that try to evaluate how pleasant is a voice from a perceptual point of view when the final application is a speech based interface. In this paper we present an objective definition for voice pleasantness based on the composition of a representative feature subset and a new automatic voice pleasantness classification and intensity estimation system. Our study is based on a database composed by European Portuguese female voices but the methodology can be extended to male voices or to other languages. In the objective performance evaluation the system achieved a 9.1% error rate for voice pleasantness classification and a 15.7% error rate for voice pleasantness intensity estimation.

Sistema de auto calibração visual para robots do ISePorto, baseado em EKF

Os sistemas de perceção existentes nos robôs autónomos, hoje em dia, são bastante complexos. A informação dos vários sensores, existentes em diferentes partes do robôs, necessitam de estar relacionados entre si face ao referencial do robô ou do mundo. Para isso, o conhecimento da atitude (posição e rotação) entre os referenciais dos sensores e o referencial do robô é um fator critico para o desempenho do mesmo. O processo de calibração dessas posições e translações é chamado calibração dos parâmetros extrínsecos. Esta dissertação propõe o desenvolvimento de um método de calibração autónomo para robôs como câmaras direcionais, como é o caso dos robôs da equipa ISePorto. A solução proposta consiste na aquisição de dados da visão, giroscópio e odometria durante uma manobra efetuada pelo robô em torno de um alvo com um padrão conhecido. Esta informação é então processada em conjunto através de um Extended Kalman Filter (EKF) onde são estimados necessários para relacionar os sensores existentes no robô em relação ao referencial do mesmo. Esta solução foi avaliada com recurso a vários testes e os resultados obtidos foram bastante similares aos obtidos pelo método manual, anteriormente utilizado, com um aumento significativo em rapidez e consistência.

Combate à fraude em jogos de casino, assistida por computador

No decorrer dos últimos anos tem-se verificado um acréscimo do número de sistemas de videovigilância presentes nos mais diversos ambientes, sendo que estes se encontram cada vez mais sofisticados. Os casinos são um exemplo bastante popular da utilização destes sistemas sofisticados, sendo que vários casinos, hoje em dia, utilizam câmeras para controlo automático das suas operações de jogo. No entanto, atualmente existem vários tipos de jogos em que o controlo automático ainda não se encontra disponível, sendo um destes, o jogo Banca Francesa. A presente dissertação tem como objetivo propor um conjunto de algoritmos idealizados para um sistema de controlo e gestão do jogo de casino Banca Francesa através do auxílio de componentes pertencentes à área da computação visual, tendo em conta os contributos mais relevantes e existentes na área, elaborados por investigadores e entidades relacionadas. No decorrer desta dissertação são apresentados quatro módulos distintos, os quais têm como objetivo auxiliar os casinos a prevenir o acontecimento de fraudes durante o decorrer das suas operações, assim como auxiliar na recolha automática de resultados de jogo. Os quatro módulos apresentados são os seguintes: Dice Sample Generator – Módulo proposto para criação de casos de teste em grande escala; Dice Sample Analyzer – Módulo proposto para a deteção de resultados de jogo; Dice Calibration – Módulo proposto para calibração automática do sistema; Motion Detection – Módulo proposto para a deteção de fraude no jogo. Por fim, para cada um dos módulos, é apresentado um conjunto de testes e análises de modo a verificar se é possível provar o conceito para cada uma das propostas apresentadas.

Characterisation of noisy speech channels in 2G and 3G mobile networks

As the wireless cellular market reaches competitive levels never seen before, network operators need to focus on maintaining Quality of Service (QoS) a main priority if they wish to attract new subscribers while keeping existing customers satisfied. Speech Quality as perceived by the end user is one major example of a characteristic in constant need of maintenance and improvement. It is in this topic that this Master Thesis project fits in. Making use of an intrusive method of speech quality evaluation, as a means to further study and characterize the performance of speech codecs in second-generation (2G) and third-generation (3G) technologies. Trying to find further correlation between codecs with similar bit rates, along with the exploration of certain transmission parameters which may aid in the assessment of speech quality. Due to some limitations concerning the audio analyzer equipment that was to be employed, a different system for recording the test samples was sought out. Although the new designed system is not standard, after extensive testing and optimization of the system's parameters, final results were found reliable and satisfactory. Tests include a set of high and low bit rate codecs for both 2G and 3G, where values were compared and analysed, leading to the outcome that 3G speech codecs perform better, under the approximately same conditions, when compared with 2G. Reinforcing the idea that 3G is, with no doubt, the best choice if the costumer looks for the best possible listening speech quality. Regarding the transmission parameters chosen for the experiment, the Receiver Quality (RxQual) and Received Energy per Chip to the Power Density Ratio (Ec/N0), these were subject to speech quality correlation tests. Final results of RxQual were compared to those of prior studies from different researchers and, are considered to be of important relevance. Leading to the confirmation of RxQual as a reliable indicator of speech quality. As for Ec/N0, it is not possible to state it as a speech quality indicator however, it shows clear thresholds for which the MOS values decrease significantly. The studied transmission parameters show that they can be used not only for network management purposes but, at the same time, give an expected idea to the communications engineer (or technician) of the end-to-end speech quality consequences. With the conclusion of the work new ideas for future studies come to mind. Considering that the fourth-generation (4G) cellular technologies are now beginning to take an important place in the global market, as the first all-IP network structure, it seems of great relevance that 4G speech quality should be subject of evaluation. Comparing it to 3G, not only in narrowband but also adding wideband scenarios with the most recent standard objective method of speech quality assessment, POLQA. Also, new data found on Ec/N0 tests, justifies further research studies with the intention of validating the assumptions made in this work.

Real-Time Visual Ground-Truth System for Indoor Robotic Applications

The robotics community is concerned with the ability to infer and compare the results from researchers in areas such as vision perception and multi-robot cooperative behavior. To accomplish that task, this paper proposes a real-time indoor visual ground truth system capable of providing accuracy with at least more magnitude than the precision of the algorithm to be evaluated. A multi-camera architecture is proposed under the ROS (Robot Operating System) framework to estimate the 3D position of objects and the implementation and results were contextualized to the Robocup Middle Size League scenario.

Calibration Method for Underwater Visual Ground-Truth System

This work presents an automatic calibration method for a vision based external underwater ground-truth positioning system. These systems are a relevant tool in benchmarking and assessing the quality of research in underwater robotics applications. A stereo vision system can in suitable environments such as test tanks or in clear water conditions provide accurate position with low cost and flexible operation. In this work we present a two step extrinsic camera parameter calibration procedure in order to reduce the setup time and provide accurate results. The proposed method uses a planar homography decomposition in order to determine the relative camera poses and the determination of vanishing points of detected lines in the image to obtain the global pose of the stereo rig in the reference frame. This method was applied to our external vision based ground-truth at the INESC TEC/Robotics test tank. Results are presented in comparison with an precise calibration performed using points obtained from an accurate 3D LIDAR modelling of the environment.