Conversação homem-máquina. Caracterização e avaliação do estado actual das soluções de speech recognition, speech synthesis e sistemas de conversação homem-máquina

A comunicação verbal humana é realizada em dois sentidos, existindo uma compreensão de ambas as partes que resulta em determinadas considerações. Este tipo de comunicação, também chamada de diálogo, para além de agentes humanos pode ser constituído por agentes humanos e máquinas. A interação entre o Homem e máquinas, através de linguagem natural, desempenha um papel importante na melhoria da comunicação entre ambos. Com o objetivo de perceber melhor a comunicação entre Homem e máquina este documento apresenta vários conhecimentos sobre sistemas de conversação Homemmáquina, entre os quais, os seus módulos e funcionamento, estratégias de diálogo e desafios a ter em conta na sua implementação. Para além disso, são ainda apresentados vários sistemas de Speech Recognition, Speech Synthesis e sistemas que usam conversação Homem-máquina. Por último são feitos testes de performance sobre alguns sistemas de Speech Recognition e de forma a colocar em prática alguns conceitos apresentados neste trabalho, é apresentado a implementação de um sistema de conversação Homem-máquina. Sobre este trabalho várias ilações foram obtidas, entre as quais, a alta complexidade dos sistemas de conversação Homem-máquina, a baixa performance no reconhecimento de voz em ambientes com ruído e as barreiras que se podem encontrar na implementação destes sistemas.

Voice conversion with pre-trained representations for audio anonymization

The recording and processing of voice data raises increasing privacy concerns for users and service providers. One way to address these issues is to move processing on the edge device closer to the recording so that potentially identifiable information is not transmitted over the internet. However, this is often not possible due to hardware limitations. An interesting alternative is the development of voice anonymization techniques that remove individual speakers characteristics while preserving linguistic and acoustic information in the data. In this work, a state-of-the-art approach to sequence-to-sequence speech conversion, ini- tially based on x-vectors and bottleneck features for automatic speech recognition, is explored to disentangle the two acoustic information using different pre-trained speech and speakers representation. Furthermore, different strategies for selecting target speech representations are analyzed. Results on public datasets in terms of equal error rate and word error rate show that good privacy is achieved with limited impact on converted speech quality relative to the original method.

Reconhecimento de língua gestual

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Informática e Computadores

Sistemas de detección y extracción semiautomática de siglas: estado de la cuestión

Informe de investigación realizado a partir de una estancia en el Équipe de Recherche en Syntaxe et Sémantique de la Université de Toulouse-Le Mirail, Francia, entre julio y setiembre de 2006. En la actualidad existen diversos diccionarios de siglas en línea. Entre ellos sobresalen Acronym Finder, Abbreviations.com y Acronyma; todos ellos dedicados mayoritariamente a las siglas inglesas. Al igual que los diccionarios en papel, este tipo de diccionarios presenta problemas de desactualización por la gran cantidad de siglas que se crean a diario. Por ejemplo, en 2001, un estudio de Pustejovsky et al. mostraba que en los abstracts de Medline aparecían mensualmente cerca de 12.000 nuevas siglas. El mecanismo de actualización empleado por estos recursos es la remisión de nuevas siglas por parte de los usuarios. Sin embargo, esta técnica tiene la desventaja de que la edición de la información es muy lenta y costosa. Un ejemplo de ello es el caso de Abbreviations.com que en octubre de 2006 tenía alrededor de 100.000 siglas pendientes de edición e incorporación definitiva. Como solución a este tipo de problema, se plantea el diseño de sistemas de detección y extracción automática de siglas a partir de corpus. El proceso de detección comporta dos pasos; el primero, consiste en la identificación de las siglas dentro de un corpus y, el segundo, la desambiguación, es decir, la selección de la forma desarrollada apropiada de una sigla en un contexto dado. En la actualidad, los sistemas de detección de siglas emplean métodos basados en patrones, estadística, aprendizaje máquina, o combinaciones de ellos. En este estudio se analizan los principales sistemas de detección y desambiguación de siglas y los métodos que emplean. Cada uno se evalúa desde el punto de vista del rendimiento, medido en términos de precisión (porcentaje de siglas correctas con respecto al número total de siglas extraídas por el sistema) y exhaustividad (porcentaje de siglas correctas identificadas por el sistema con respecto al número total de siglas existente en el corpus). Como resultado, se presentan los criterios para el diseño de un futuro sistema de detección de siglas en español.

ÄÄNEEN PERUSTUVA KÄYTTÄJÄN TODENTAMINEN PUHELINVERKON LISÄARVOPALVELUISSA

Tässä diplomityössä perehdytään puhujantunnistukseen ja sen käyttökelpoisuuteen käyttäjän henkilöllisyyden todentamisessa osana puhelinverkon lisäarvopalveluja. Puhelimitse ohjattavat palvelut ovat yleensä perustuneet puhelimen näppäimillä lähetettäviin äänitaajuusvalintoihin. Käyttäjän henkilöllisyydestä on voitu varmistua esimerkiksi käyttäjätunnuksen ja salaisen tunnusluvun perusteella. Tulevaisuudessa palvelut voivat perustua puheentunnistukseen, jolloin myös käyttäjän todentaminen äänen perusteella vaikuttaa järkevältä. Työssä esitellään aluksi erilaisia biometrisiä tunnistamismenetelmiä. Työssä perehdytään tarkemmin äänen perusteella tapahtuvaan puhujan todentamiseen. Työn käytännön osuudessa toteutettiin puhelinverkon palveluihin soveltuva puhujantodennussovelluksen prototyyppi. Työn tarkoituksena oli selvittää teknologian käyttömahdollisuuksia sekä kerätä kokemusta puhujantodennuspalvelun toteuttamisesta tulevaisuutta silmällä pitäen. Prototyypin toteutuksessa ohjelmointikielenä käytettiin Javaa.

Un outil d’évaluation neurocognitive des interactions humain-machine

De plus en plus de recherches sur les Interactions Humain-Machine (IHM) tentent d’effectuer des analyses fines de l’interaction afin de faire ressortir ce qui influence les comportements des utilisateurs. Tant au niveau de l’évaluation de la performance que de l’expérience des utilisateurs, on note qu’une attention particulière est maintenant portée aux réactions émotionnelles et cognitives lors de l’interaction. Les approches qualitatives standards sont limitées, car elles se fondent sur l’observation et des entrevues après l’interaction, limitant ainsi la précision du diagnostic. L’expérience utilisateur et les réactions émotionnelles étant de nature hautement dynamique et contextualisée, les approches d’évaluation doivent l’être de même afin de permettre un diagnostic précis de l’interaction. Cette thèse présente une approche d’évaluation quantitative et dynamique qui permet de contextualiser les réactions des utilisateurs afin d’en identifier les antécédents dans l’interaction avec un système. Pour ce faire, ce travail s’articule autour de trois axes. 1) La reconnaissance automatique des buts et de la structure de tâches de l’utilisateur, à l’aide de mesures oculométriques et d’activité dans l’environnement par apprentissage machine. 2) L’inférence de construits psychologiques (activation, valence émotionnelle et charge cognitive) via l’analyse des signaux physiologiques. 3) Le diagnostic de l‘interaction reposant sur le couplage dynamique des deux précédentes opérations. Les idées et le développement de notre approche sont illustrés par leur application dans deux contextes expérimentaux : le commerce électronique et l’apprentissage par simulation. Nous présentons aussi l’outil informatique complet qui a été implémenté afin de permettre à des professionnels en évaluation (ex. : ergonomes, concepteurs de jeux, formateurs) d’utiliser l’approche proposée pour l’évaluation d’IHM. Celui-ci est conçu de manière à faciliter la triangulation des appareils de mesure impliqués dans ce travail et à s’intégrer aux méthodes classiques d’évaluation de l’interaction (ex. : questionnaires et codage des observations).

Development of a Biometric Personal Authentication System Based on Fingerprint and Speech

Biometrics deals with the physiological and behavioral characteristics of an individual to establish identity. Fingerprint based authentication is the most advanced biometric authentication technology. The minutiae based fingerprint identification method offer reasonable identification rate. The feature minutiae map consists of about 70-100 minutia points and matching accuracy is dropping down while the size of database is growing up. Hence it is inevitable to make the size of the fingerprint feature code to be as smaller as possible so that identification may be much easier. In this research, a novel global singularity based fingerprint representation is proposed. Fingerprint baseline, which is the line between distal and intermediate phalangeal joint line in the fingerprint, is taken as the reference line. A polygon is formed with the singularities and the fingerprint baseline. The feature vectors are the polygonal angle, sides, area, type and the ridge counts in between the singularities. 100% recognition rate is achieved in this method. The method is compared with the conventional minutiae based recognition method in terms of computation time, receiver operator characteristics (ROC) and the feature vector length. Speech is a behavioural biometric modality and can be used for identification of a speaker. In this work, MFCC of text dependant speeches are computed and clustered using k-means algorithm. A backpropagation based Artificial Neural Network is trained to identify the clustered speech code. The performance of the neural network classifier is compared with the VQ based Euclidean minimum classifier. Biometric systems that use a single modality are usually affected by problems like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks. Multifinger feature level fusion based fingerprint recognition is developed and the performances are measured in terms of the ROC curve. Score level fusion of fingerprint and speech based recognition system is done and 100% accuracy is achieved for a considerable range of matching threshold

Improved Biometric Authentication System Using Multimodal Cue Integration

Biometrics is an efficient technology with great possibilities in the area of security system development for official and commercial applications. The biometrics has recently become a significant part of any efficient person authentication solution. The advantage of using biometric traits is that they cannot be stolen, shared or even forgotten. The thesis addresses one of the emerging topics in Authentication System, viz., the implementation of Improved Biometric Authentication System using Multimodal Cue Integration, as the operator assisted identification turns out to be tedious, laborious and time consuming. In order to derive the best performance for the authentication system, an appropriate feature selection criteria has been evolved. It has been seen that the selection of too many features lead to the deterioration in the authentication performance and efficiency. In the work reported in this thesis, various judiciously chosen components of the biometric traits and their feature vectors are used for realizing the newly proposed Biometric Authentication System using Multimodal Cue Integration. The feature vectors so generated from the noisy biometric traits is compared with the feature vectors available in the knowledge base and the most matching pattern is identified for the purpose of user authentication. In an attempt to improve the success rate of the Feature Vector based authentication system, the proposed system has been augmented with the user dependent weighted fusion technique.

Fingerprint Segmentation

In this thesis, a new algorithm has been proposed to segment the foreground of the fingerprint from the image under consideration. The algorithm uses three features, mean, variance and coherence. Based on these features, a rule system is built to help the algorithm to efficiently segment the image. In addition, the proposed algorithm combine split and merge with modified Otsu. Both enhancements techniques such as Gaussian filter and histogram equalization are applied to enhance and improve the quality of the image. Finally, a post processing technique is implemented to counter the undesirable effect in the segmented image. Fingerprint recognition system is one of the oldest recognition systems in biometrics techniques. Everyone have a unique and unchangeable fingerprint. Based on this uniqueness and distinctness, fingerprint identification has been used in many applications for a long period. A fingerprint image is a pattern which consists of two regions, foreground and background. The foreground contains all important information needed in the automatic fingerprint recognition systems. However, the background is a noisy region that contributes to the extraction of false minutiae in the system. To avoid the extraction of false minutiae, there are many steps which should be followed such as preprocessing and enhancement. One of these steps is the transformation of the fingerprint image from gray-scale image to black and white image. This transformation is called segmentation or binarization. The aim for fingerprint segmentation is to separate the foreground from the background. Due to the nature of fingerprint image, the segmentation becomes an important and challenging task. The proposed algorithm is applied on FVC2000 database. Manual examinations from human experts show that the proposed algorithm provides an efficient segmentation results. These improved results are demonstrating in diverse experiments.

Reconhecimento de voz através de unidades menores do que a palavra, utilizando Wavelet Packet e SVM, em uma nova estrutura hierárquica de decisão

The automatic speech recognition by machine has been the target of researchers in the past five decades. In this period have been numerous advances, such as in the field of recognition of isolated words (commands), which has very high rates of recognition, currently. However, we are still far from developing a system that could have a performance similar to the human being (automatic continuous speech recognition). One of the great challenges of searches for continuous speech recognition is the large amount of pattern. The modern languages such as English, French, Spanish and Portuguese have approximately 500,000 words or patterns to be identified. The purpose of this study is to use smaller units than the word such as phonemes, syllables and difones units as the basis for the speech recognition, aiming to recognize any words without necessarily using them. The main goal is to reduce the restriction imposed by the excessive amount of patterns. In order to validate this proposal, the system was tested in the isolated word recognition in dependent-case. The phonemes characteristics of the Brazil s Portuguese language were used to developed the hierarchy decision system. These decisions are made through the use of neural networks SVM (Support Vector Machines). The main speech features used were obtained from the Wavelet Packet Transform. The descriptors MFCC (Mel-Frequency Cepstral Coefficient) are also used in this work. It was concluded that the method proposed in this work, showed good results in the steps of recognition of vowels, consonants (syllables) and words when compared with other existing methods in literature

A low-cost 3D reconstruction system using a single-shot projection of a pattern matrix

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Strategy to detect ground control in digital images

The identification of ground control on photographs or images is usually carried out by a human operator, who uses his natural skills to make interpretations. In Digital Photogrammetry, which uses techniques of digital image processing extraction of ground control can be automated by using an approach based on relational matching and a heuristic that uses the analytical relation between straight features of object space and its homologous in the image space. A build-in self-diagnosis is also used in this method. It is based on implementation of data snooping statistic test in the process of spatial resection using the Iterated Extended Kalman Filtering (IEKF). The aim of this paper is to present the basic principles of the proposed approach and results based on real data.

Anaerobic threshold estimation by statistical modelling.

Anaerobic threshold (AT) is usually estimated as a change point problem by visual analysis of the cardiorespiratory response to incremental dynamic exercise. In this study, two phase linear (TPL) models of the linear-linear and linear-quadratic type were used for the estimation of AT. The correlation coefficient between the classical and statistical approaches was 0.88, and 0.89 after outlier exclusion. The TPL models provide a simple method for estimating AT that can be easily implemented using a digital computer for the automatic pattern recognition of AT.

On the determination of epsilon during discriminative GMM training

Discriminative training of Gaussian Mixture Models (GMMs) for speech or speaker recognition purposes is usually based on the gradient descent method, in which the iteration step-size, ε, uses to be defined experimentally. In this letter, we derive an equation to adaptively determine ε, by showing that the second-order Newton-Raphson iterative method to find roots of equations is equivalent to the gradient descent algorithm. © 2010 IEEE.