Die vorliegende Arbeit ist im Umfeld der MVC Mobile VideoCommunication GmbH entstanden und thematisiert die Strategieentwicklung zur Auto-matisierung einzelner Geschäftsprozesse mithilfe des ERP-Systems Microsoft Dynamics NAV und einer darauf aufsetzenden Branchenlösung (SITE). Das Unternehmen steht derzeit durch die Marktsituation der Anforderung gegenüber, die internen Geschäfts-prozesse zu automatisieren und damit effizienter zu gestalten, um die Produktivität der Mitarbeiter zu steigern. Innerhalb dieser Arbeit wurden die zu betrachtenden Geschäftsprozesse zunächst fundiert ausgewählt, auf Automatisierungspotentiale analysiert und auf Stärken und Schwächen untersucht. Schließlich wurde mithilfe bestehender Standard-Funktionalitäten und/oder Anpassungen an der Branchenlösung SITE (basierend auf dem ERP-System Microsoft Dynamics NAV) ein prototypischer Entwurf dieser Automatisierungen umgesetzt. Für die Auswahl der potentialreichsten Prozessschritte hat sich die Verfahrensmethode des Activity Samplings als nützlich erwiesen, durch die mithilfe stichproben-artiger Erfassung der jeweiligen Arbeitsschritte, zu zufällig ausgewählten Zeitpunkten, die Tätigkeitsverteilung ermittelt werden kann. Die dabei am stärksten auftretenden Prozessabläufe wurden daraufhin detaillierter untersucht, durch die Anforderungen an die Automatisierungspotentiale formuliert werden konnten. Anschließend wurden diese Anforderungen technisch konzeptioniert und in der Programmiersprache C/AL über verschiedene Lösungen entwickelt. Um die Zukunftssicherheit der realisierten Lösung sicherzustellen, empfiehlt sich eine perspektivische Migration auf die Extension-Technologie, die das Ziel verfolgt, den bisher aufwändigen Update-Prozess wesentlich zu verschlanken.

This paper describes a tool for analysis of solutions to programming tasks. The analysis addresses both the code and the generated graphical output. First results on the correlation between quality of code and complexity of the output are reported.

This paper describes a graphical user interface based on a rectangular board with symbols. A set of functions is provided to change the symbols in shape, color and size. The approach is used in courses for programming beginners.

Dieses Buch bietet einen Schnelleinstieg in die Java-Programmierung. Anhand einer einfachen Schnittstelle zur grafischen Programmierung, dem sogenannten Plotter, werden anschaulich grafische Darstellungen mit Texten, Fonts, Zeichenstilen und Farben erstellt.

In diesem Kapitel werden einige Anwendungsbeispiele vorgestellt. Die ersten Beispiele verwenden im Wesentlichen spezielle Möglichkeiten wie Zeichenstile, Verwendung von Mauseingaben und Einbau von Bildern. Die beiden letzten Beispiele zeigen die Visualisierung von Algorithmen.

In diesem Beitrag wird uber erste Erfahrungen mit der Realisierung von Sprachdialogen mit dem Web-Entwicklungs-Framework Grails berichtet. Als Beispiel werden Anfragen zu einem Bestand von Buchern betrachtet. In eine entsprechende Grails-Anwendung werden gemas des X+V Konzepts zusatzliche VoiceXML-Teile in die generierten Webseiten eingefugt. Mit einem entsprechenden Browser kann man dann die Webanwendung auch per Spracheingabe steuern. Dank der guten Unterstutzung durch entsprechende Konzepte in Groovy ist die Erweiterung um VoiceXML-Teile sehr einfach. Insgesamt gesehen erweist sich der Weg von der Spezifikation des Datenmodells bis zu ersten Sprachdialogen als kurz und gradlinig.

In this paper, we present our concept for a sequence of experiments with speech recognizers used in teaching speech recognition techniques. The experiments are performed with a combination of own tools and the hidden Markov toolkit (HTK). The first experiment demonstrates speaker dependent recognition based on the dynamic time warp algorithm. In the course of this experiment all utterances from the students are recorded and used to build up a data base. Both the recognizer and the tool used for viewing and editing the speech data are written in Java making them platform independent and easy to extend. The recorded speech data is then utilized to train and test a speaker independent recognizer.

Last year, SpLC - an ISCA Special Interest Group (SIG) centered around Speaker and Language Characterization was born. The aims of this paper are to present the SpLC SIG, its objectives, and the work done during the first year.

In this paper we summarize the experiences gained from a field trial of a speaker verification system. In the test implementation access to two rooms at the University of Frankfurt had been controlled by a speaker verification system. The paper is organized as follows: Firstly, we will describe the system concepts and implementation issues. Secondly, results of the user evaluation are reported. During the field trial all speech data was recorded. The data base created in this way has been used extensively for simulation experiments. In chapter 4 we will describe recent experiments focusing on the use of Hidden Markov Models.

languages are Danish, British English, Finnish, Flemish/Dutch, French, German, Greek, Italian, Spanish and American English. For each language 600 sessions will be recorded (from at least 300 speakers) in seven characteristic environments (low speed, high speed with audio equipment on, etc.). This paper gives an overview of the project with a focus on the production phases (recording platforms, speaker recruitment, annotation and distribution).

The main objective of SpeechDat-Car is to develop a set of speech databases to support training and testing of multilingual speech recognition applications in the car environment. SpeechDat-Car started in April 1998 in the 4th EC framework under project code LE4-8334. The duration of the project is 30 months. Equivalent and similar resources for nine languages will be created: Danish, English, Finnish, Flemish/Dutch, French, German, Greek, Italian and Spanish. For each language 600 sessions will be recorded from at least 300 speakers. SpeechDat-Car commits itself to a strict validation protocol to ensure optimal quality and exchangeability of the databases. The first milestone in this respect is the validation of the recording platform and of a small subset of initial recordings. This paper briefly describes the database design and the recording platforms; next, it focuses on the objectives, the procedure, and some of the results of the early validation stage.

In this paper we use whole word and subword hidden Markov models for text dependent speaker verification. In this application usually only a small amount of training data is available for each model. In order to cope with this limitation we propose a intermediate functional representation of the training data allowing the robust initialization of the models. This new approach is tested with two databases and is compared both with standard training techniques and the dynamic time warp method. Secondly, we give results for two types of subword units. The scores of these units are combined in two different ways to obtain word error rates.

In this paper we present a time continuous extension of the hidden Markov model approach in order to obtain a better representation of the continuous nature of the speech process. The discrete state sequence of the hidden Markov model is replaced by a continuous parameter, varying between 0 and 1. For an utterance and a given word model an optimum mapping of the feature vectors to the continuous axis is found and the likelihood is calculated based on this mapping. As a first test of this very general approach we extended the hidden Markov model by first mapping the states onto the new axis. Values between the states are then obtained by interpolation between the states. As alternatives we considered interpolation of either the likelihood values of the state density functions and/or of the parameters of the density functions itself. The approach was tested in a speaker independent isolated word recognition system.

Examines the influence of different coders in the range from 64 kbit/sec to 4.8 kbit/sec on both a speaker independent isolated word recognizer and a speaker verification system. Applying systems trained with 64 kbit/sec to e.g. the 4.8 kbit/sec data increases the error rate of the word recognizer by a factor of three. For rates below 13 kbit/sec the speaker verification is more affected than the word recognition. The performance improves significantly if word models are provided for the individual coding conditions. Therefore, the authors use a Gaussian classifier for estimation of the coding condition of a test utterance. The combination of this classifier and coder specific word models yields a high overall recognition performance.< >

In this paper we discuss various aspects of the application of tied density Hidden Markov Models to automatic speech recognition. Using a speaker independent, isolated word recognition system as an example, different densities are compared with respect to recognition performance and computational complexity. Next, we present an approach to replace similar densities by a common representative. Finally, results are given for extending the vocabulary using the densities derived from the basic set of words.