Fakultät für Informatik
Refine
Year of publication
Document Type
- Conference Proceeding (82)
- Article (peer reviewed) (9)
- Book (8)
- Contribution to a Periodical (7)
- Other (4)
- Part of a Book (3)
Language
- English (113) (remove)
Is part of the Bibliography
- no (113)
Keywords
- Speech Recognition (18)
- CFT (6)
- Database (5)
- Microsoft (5)
- Sql server (5)
- Fault trees (4)
- Safety-critical systems (4)
- Software Development (4)
- Augmented Reality (AR) (3)
- Automatic Speech Recognition (3)
Institute
Efficient safety analyses of complex software intensive embedded systems are still a challenging task. This article illustrates how model-driven development principles can be used in safety engineering to reduce cost and effort. To this end, the article shows how well accepted safety engineering approaches can be shifted to the level of model-driven development by integrating safety models into functional development models. Namely, we illustrate how UML profiles, model transformations, and techniques for multi language development can be used to seamlessly integrate component fault trees into the UML.
The open and cooperative nature of Cyber-Physical Systems (CPS) poses new challenges in assuring dependability. The DEIS project (Dependability Engineering Innovation for automotive CPS. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732242, see http://www.deis-project.eu) addresses these challenges by developing technologies that form a science of dependable system integration. In the core of these technologies lies the concept of a Digital Dependability Identity (DDI) of a component or system. DDIs are modular, composable, and executable in the field facilitating (a) efficient synthesis of component and system dependability information over the supply chain and (b) effective evaluation of this information in-the-field for safe and secure composition of highly distributed and autonomous CPS. The paper outlines the DDI concept and opportunities for application in four industrial use cases.
Stuttering is a complex speech disorder identified by repetitions, prolongations of sounds, syllables or words and blockswhile speaking. Specific stuttering behaviour differs strongly,thus needing personalized therapy. Therapy sessions requirea high level of concentration by the therapist. We introduce STAN, a system to aid speech therapists in stuttering therapysessions. Such an automated feedback system can lower the cognitive load on the therapist and thereby enable a more consistent therapy as well as allowing analysis of stuttering over the span of multiple therapy sessions.
Java Server Faces
(2004)
Components and component-based technologies (componentware) are well-known and widely used in software development. There is a large amount of work and research in componentware. The number of available componentware approaches increases steadily and it is quite difficult to keep track of current trends in this area. In this paper, we survey the current state of the art in componentware, introduce and compare several well-known componentware approaches and classify them according to outstanding characteristics. We discuss a list of open issues in resarch and practical use of componentware and offer some proposals for further development. In our practical considerations we focus on embedded systems and business information systems because most of our partners in industry work in one of these two domains. We hope to start a broader discussion on componentware and to get a common understanding, which open issues are most important in research and industry (as a research agenda).
Nowadays, in software development usually various models and description fragments are created. Some of these artifacts describe the core of the application, such as the data model or the user interaction model. Other artifacts describe cross-cutting concerns, such as security or the requirement: “every change of data has to be confirmed by the user, before it is written into the database”. During the development process these artifacts are combined, transformed, and finally implemented manually or even automatically. For instance a designer may combine a model of a dialog component specifying an action, that changes data, with a common description of a generic confirm dialog. The integrated dialog description may be afterwards implemented by a programmer. The manual combination of both artifacts and the transformation of the combined description into code are errorprone and hard to change. Industry basically tests or actually uses two approaches for the combination today: 1. At the level of code and execution Aspect-Oriented Programming (AOP) is used [KLM+97]. An aspect defines a cross-cutting concern and the weaving instructions. A code weaver provides the actual weaving at compile or runtime. 2. At the level of design models and analysis models Model-Driven Software Development (MDSD) is used [KWB03]. A model in MDSD is a first class development artifact. Thus models are significantly more abstract than the implementation of code. However, these models cannot be executed. Hence, a abstract model is transformed into another, typically more detailed. A series of such transformations results in executable code. Thereby, a model transformer or a code generator reads some of the artifacts. The other artifacts and the combination rules are implemented in transformation rules or code generation templates (or somewhere else in the transformation / generation approach).
In this paper we describe Erlangen-CLP, a large speech database of children with Cleft Lip and Palate. More than 800 German children with CLP (most of them between 4 and 18 years old) and 380 age matched control speakers spoke the semi-standardized PLAKSS test that consists of words with all German phonemes in different positions. So far 250 CLP speakers were manually transcribed, 120 of these were analyzed by a speech therapist and 27 of them by four additional therapists. The tharapists marked 6 different processes/criteria like pharyngeal backing and hypernasality which typically occur in speech of people with CLP. We present detailed statistics about the the marked processes and the inter-rater agreement.
Towards a Language-independent Intelligibility Assessment of Children with Cleft Lip and Palate
(2009)
We describe a novel evaluation system for the intelligibility assessment of children with CLP on standardized tests. The system is solely based on standard cepstral features in form of MFCCs. No other information like word alignments is used. So the system can be easily adapted to other languages. For each child one GMM is created by adaptation of a UBM to the speaker-specific MFCCs. The components of this GMM are concatenated in order to create a so-called GMM supervector. These GMM supervectors are then used as meta features for an SVR. We evaluated our language-independent system on two different datasets of children suffering from CLP. One dataset contains recordings of 35 German children, where the children named different pictograms. The other dataset contains recordings of 14 Italian speaking children, who repeated standardized sentences. On both datasets we achieved high correlations: up to 0.81 for the German dataset and 0.83 for the Italian dataset.
Cleft Lip and Palate (CLP) is among the most frequent congenital abnormalities. The impaired facial development affects the articulation, with different phonemes being impacted inhomogeneously among different patients. This work focuses on automatic phoneme analysis of children with CLP for a detailed diagnosis and therapy control. In clinical routine, the state-of-the-art evaluation is based on perceptual evaluations. Perceptual ratings act as ground-truth throughout this work, with the goal to build an automatic system that is as reliable as humans. We propose two different automatic systems focusing on modeling the articulatory space of a speaker: one system models a speaker by a GMM, the other system employs a speech recognition system and estimates fMLLR matrices for each speaker. SVR is then used to predict the perceptual ratings. We show that the fMLLR-based system is able to achieve automatic phoneme evaluation results that are in the same range as perceptual inter-rater-agreements.
This paper focuses on the automatic detection of a person's blood level alcohol based on automatic speech processing approaches. We compare 5 different feature types with different ways of modeling. Experiments are based on the ALC corpus of IS2011 Speaker State Challenge. The classification task is restricted to the detection of a blood alcohol level above 0.5‰. Three feature sets are based on spectral observations: MFCCs, PLPs, TRAPS. These are modeled by GMMs. Classification is either done by a Gaussian classifier or by SVMs. In the later case classification is based on GMM-based supervectors, i.e. concatenation of GMM mean vectors. A prosodic system extracts a 292-dimensional feature vector based on a voiced-unvoiced decision. A transcription-based system makes use of text transcriptions related to phoneme durations and textual structure. We compare the stand-alone performances of these systems and combine them on score level by logistic regression. The best stand-alone performance is the transcriptionbased system which outperforms the baseline by 4.8% on the development set. A Combination on score level gave a huge boost when the spectral-based systems were added (73.6%). This is a relative improvement of 12.7% to the baseline. On the test-set we achieved an UA of 68.6% which is a significant improvement of 4.1% to the baseline system.