Karmele López de Ipiña

Enhancing the Feature Extraction Process for Automatic Speech Recognition with Fractal Dimensions

Mel frequency cepstral coefficients (MFCCs) are a standard tool for automatic speech recognition (ASR), but they fail to capture part of the dynamics of speech. The nonlinear nature of speech suggests that extra information provided by some nonlinear features could be especially useful when training data are scarce or when the ASR task is very complex. In this paper, the Fractal Dimension of the observed time series is combined with the traditional MFCCs in the feature vector in order to enhance the performance of two different ASR systems. The first is a simple system of digit recognition in Chinese, with very few training examples, and the second is a large vocabulary ASR system for Broadcast News in Spanish.

Combining Mel frequency Cepstral coefficients and fractal dimensions for automatic speech recognition

Hidden Markov Models and Mel Frequency Cepstral Coefficients (MFCCs) are a sort of standard for Automatic Speech Recognition (ASR) systems, but they fail to capture the nonlinear dynamics of speech that are present in the speech waveforms. The extra information provided by the nonlinear features could be especially useful when training data is scarce, or when the ASR task is very complex. In this work, the Fractal Dimension (FD) of the observed time series is combined with the traditional MFCCs in the feature vector in order to enhance the performance of two different ASR systems: the first one is a very simple one, with very few training examples, and the second one is a Large Vocabulary Continuous Speech Recognition System for Broadcast News.

Skill based robot programming: Assembly, vision and Workspace Monitoring skill interaction

Abstract The skill based programming eases the robot program generation, its similarity to human behavior allows non expert operators maintaining, adapting or creating robotic applications. The use of skills requires different approaches for the interaction between them, especially for sharing information. The presented approach combines the skill based programming using a state machine for low level robot execution management. With the proposed framework the interaction and communication between skills is improved. The work presented below is focused on the use of vision skills and safe Workspace Monitoring, for addressing a real use case where interaction with robot motions (organized as assembly skills) is required.

State Machine Based Architecture to Increase Flexibility of Dual-Arm Robot Programming

This paper introduces a state machine based architecture with the aim of increasing flexibility of dual-arm robot programming. The proposed architecture allows absolute control of the execution, easing coordination of the arms if necessary. This work attempts to deal with dual-arm robotic programming challenges, providing a robust and reliable core which is able to interconnect different software modules where each one provides different capabilities. A pilot station is under development at Airbus Operations plant in Puerto Real, Spain.

Phonation biomechanic analysis of Alzheimer's Disease cases

Speech production in patients suffering of dementias of Alzheimer?s type is known to experience noticeable changes with respect to normative speakers. Classically this kind of speech has been described as presenting altered prosody, rhythmic pace, anomy, or impaired semantics. Phonation, conceived as the production of voice in voiced speech fragments remains as an unexplored field. The aim of the present paper is to open a preliminary study presenting biomechanical estimates from phonation produced by two patients (male and female) suffering Alzheimer?s Disease (AD), contrasted on two controls of both genders (CS: control speakers). A vocal fold biomechanical model is inverted to facilitate estimates of the vocal fold stiffness to analyze significant segments of phonated speech as long vowels and fillers. The estimates of both the AD patients and CS subjects are contrasted on a database of phonation features from a normative speaker population of both genders, as well as in paired tests contrasting AD and CS subjects. Results show the possibility of establishing significant discrimination between AD and CS when using f0, as well as vocal fold body stiffness, although this last feature seems to be more relevant and shows larger statistical significance.

Acoustic Phonetic Decoding Oriented to Multilingual Speech Recognition in the Basque Context

The development of Large Vocabulary Continuous Speech Recognition systems involves issues as: Acoustic Phonetic Decoding, Language Modelling or the development of appropriated Language Resources. In the state of the art, new techniques for reusing Language Resources of more resourced related languages is becoming of great interest, and there is also a growing interest on Multilingual systems. This paper describes the initial experiments on multilingual recognition and cross-lingual adaptation carried out in order to create a robust Multilingual Speech Recognition system for the Basque context. The interest on Multilingual Systems arouses because there are three official languages in the Basque Country (Basque, Spanish, and French), and there is much linguistic interaction among them, even if Basque has very different roots than the other two languages.

LAGUNTXO: A Rule-Based Intelligent Tutoring System Oriented to People with Intellectual Disabilities

In order to face the problems that people with disabilities find in their integration into working environments, one of the key issues is the implementation of solutions offered by new technologies by using what experts call Support Technologies. The development of Intelligent Tutoring Systems (ITS) based on mobile platforms offers new perspectives for better integration of people with disabilities. The LAGUNTXO System aims to achieve the performance of human tutors, going a step beyond classical tutoring systems which perform organizational tasks. Due to the wide diversity related to people with disabilities, an intelligent structure that may achieve a convenient tutoring system configuration for each case has been incorporated. With an appropriate design of the structure and architecture of this task handler, it is very easy to operate by stakeholders. An automaton-based mechanism has been performed to technologically adapt the large amount of possibilities related to the interaction between people with disabilities, the task that is going to be made autonomously by these people, and the mobile system elements. In this paper, LAGUNTXO architecture, operational ways, and several use cases are presented.

Tutor Project: An Intelligent Tutoring System to Improve Cognitive Disabled People Integration

Nowadays, the integration of people with cognitive disabilities, especially in the work environment in a growing competitive market, is a difficult task. The TUTOR project is addressed to the development and testing of an Intelligent Tutoring System (ITS). The ITS runs on a handheld device and its aim is to increase the autonomy of people with cognitive disabilities in labour and daily life activities, therefore, improving the social and labour integration of this collective and its quality of live. This paper describes the objectives of this project, the methodology followed, some preliminary achieved results and the future planned activities of this research group.

Enhanced Flexibility and Reusability through State Machine-Based Architectures for Multisensor Intelligent Robotics

This paper presents a state machine-based architecture, which enhances the flexibility and reusability of industrial robots, more concretely dual-arm multisensor robots. The proposed architecture, in addition to allowing absolute control of the execution, eases the programming of new applications by increasing the reusability of the developed modules. Through an easy-to-use graphical user interface, operators are able to create, modify, reuse and maintain industrial processes, increasing the flexibility of the cell. Moreover, the proposed approach is applied in a real use case in order to demonstrate its capabilities and feasibility in industrial environments. A comparative analysis is presented for evaluating the presented approach versus traditional robot programming techniques.

Skills for vision-based applications in robotics application to aeronautics assembly pilot station

This paper presents an approach which allows solving different computer vision problems organized in skills to execute them in an industrial robot. Vision applications are generally very specific and very dependent of the problem. The the use of skill-based programming is attempting to ease the use of vision in robotics field. Through this abstraction level, vision skills can be reused in different robots and applications. To demonstrate it, two skill are presented: 3D CAD Matching and feature detection. Additionaly the integration of these skills in ROS is presented and demonstrated in an aeronautics assembly industrial application.