Fakultät für Informatik
Refine
Year of publication
Document Type
- Conference Proceeding (90)
- Book (21)
- Article (peer reviewed) (11)
- Other (10)
- Contribution to a Periodical (9)
- Part of a Book (4)
- Doctoral Thesis (2)
- Working Paper (1)
Is part of the Bibliography
- no (148)
Keywords
- Speech Recognition (18)
- CFT (6)
- Software Development (6)
- Database (5)
- Microsoft (5)
- Sql server (5)
- Augmented Reality (AR) (4)
- Fault trees (4)
- Mobile Robot (4)
- Robotic Research (4)
Institute
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.
Time series are series of values ordered by time. This kind of data can be found in many real world settings. Classifying time series is a difficult task and an active area of research. This paper investigates the use of transfer learning in Deep Neural Networks and a 2D representation of time series known as Recurrence Plots. In order to utilize the research done in the area of image classification, where Deep Neural Networks have achieved very good results, we use a Residual Neural Networks architecture known as ResNet. As preprocessing of time series is a major part of every time series classification pipeline, the method proposed simplifies this step and requires only few parameters. For the first time we propose a method for multi time series classification: Training a single network to classify all datasets in the archive with one network. We are among the first to evaluate the method on the latest 2018 release of the UCR archive, a well established time series classification benchmarking dataset.
Ergebnis der Arbeit ist eine interdisziplinäre Zusammenschau zum Erkenntnisobjekt "multimediale Lern- und Masseninformationssysteme" und darauf aufbauend die Vorstellung eines Vorgehensmodell zur Konstruktion dieser Systeme und die Einbettung dieses Modells in ein bestehendes Systemplanungskonzept.
Dazu wird in der Arbeit zunächst der Begriff Multimedia anhand von allgemeinen Kriterien der Mensch-Maschine-Mensch - Kommunikation eingegrenzt und definiert. Ergebnis ist eine Systematik zur Einordnung von wissenschaftlichen Forschungsgebieten in diesem Bereich. Im zweiten Schritt erfolgt eine Untersuchung lerntheoretischer Konzepte anhand eines fünfdimensionalen Rasters. Ergebnis sind zwei Modelle, die sich zur elektronisch unterstützten Wissensvermittlung im allgemeinen eignen. Im dritten Schritt erfolgt eine Auseinandersetzung mit Informationsdarstellungen und Interaktionsmöglichkeiten an der Mensch-Maschine-Schnittstelle. Dazu wird ein konsistentes Raster erarbeitet, anhand dessen wahrnehmungspsychologische und technische Parameter von Informationsdarstellungen und Interaktionsmöglichkeiten untersucht werden. Ergebnis ist die Beschreibung von einem aus der Theater-, Film- und Fernsehbranche adaptierten Prozeß zur Erstellung eines multimedialen Drehbuchs, dem Storyboard. Der vierte Schritt beschreibt die Kombination der lerntheoretischen Konzepte mit dem Prozeß des Storyboardings multimedialer Anwendungen und die Einbettung in ein systemplanerisches Vorgehen dazu. Ergebnis ist ein Phasenkonzept zur Systemplanung multimedialer Lern- und Masseninformationssysteme.
This paper is an interdisciplinary synopsis about multimedia learning systems and mass information systems, and presents an action model for construction of these systems and the embedding of this model in an existing concept of system planning.
First step in the paper is the containment and definition of the term ‘multimedia’ on the basis of general criterions of the human-machine-human communication. Result is a taxonomy to classify scientific research areas in this field.
The second part follows an examination of different concepts of learning theories by means of a five dimensional raster. Output of this examination are two models fitting for computer based learning in general.
The third part discusses information presentation and interaction possibilities at the human - machine - interface. Therefore a consistent raster is acquired, where psychological perception parameters and technical parameters of information presentations and interaction possibilities are examined. This results in the so-called storyboarding, which is the description of a process adapted from theater, film and TV for developing a multimedia script.
The combination of learntheoretical concepts with the process of storyboarding of multimedia applications and the embedding in a system planning action model is described in the fourth part. The result of this last part shows a phase concept for system planning of multimedia learning systems and mass information systems.
In this paper we apply diagnostic analysis to gain a deeper understanding of the performance of the the keyword search system that we have developed for conversational telephone speech in the IARPA Babel program. We summarize the Babel task, its primary performance metric, “actual term weighted value” (ATWV), and our recognition and keyword search systems. Our analysis uses two new oracle ATWV measures, a bootstrap-based ATWV confidence interval, and includes a study of the underpinnings of the large ATWV gains due to system combination. This analysis quantifies the potential ATWV gains from improving the number of true hits and the overall quality of the detection scores in our system's posting lists. It also shows that system combination improves our systems' ATWV via a small increase in the number of true hits in the posting lists.
A growing number of universities and other educational institutions provide recordings of lectures and seminars as an additional resource to the students. In contrast to educational films that are scripted, directed and often shot by film professionals, these plain recordings are typically not post-processed in an editorial sense. Thus, the videos often contain longer periods of inactivity or silence, unnecessary repetitions, or corrections of prior mistakes. This paper describes the FAU Video Lecture Browser system, a web-based platform for the interactive assessment of video lectures, that helps to close the gap between a plain recording and a useful e-learning resource by displaying automatically extracted and ranked key phrases on an augmented time line based on stream graphs. In a pilot study, users of the interface were able to complete a topic localization task about 29 % faster than users provided with the video only while achieving about the same accuracy. The user interactions can be logged on the server to collect data to evaluate the quality of the phrases and rankings, and to train systems that produce customized phrase rankings.
The use of multimedia can significantly improve the quality of case studies, especially with regard to their presentation of reality. The development of multimedia case studies poses a challenge of both a creative and a technical nature. This paper describes the various stages of the development of the case study itself as well as an action model which supports the application of didactical aims in a multimedia case study.
The CALO meeting assistant provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper summarizes the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, question-answer pair identification, action item recognition, decision extraction, and summarization.
The CALO Meeting Assistant (MA) provides for distributed meeting capture, annotation, automatic transcription and semantic analysis of multiparty meetings, and is part of the larger CALO personal assistant system. This paper presents the CALO-MA architecture and its speech recognition and understanding components, which include real-time and offline speech transcription, dialog act segmentation and tagging, topic identification and segmentation, question-answer pair identification, action item recognition, decision extraction, and summarization.
The classical results of the binomial and negative binomial probability distribution are generalized by means of homogeneous Discrete Time Markov Chains to series of stochastically independent random trials. These have not only two possible outcomes but two groups of them -- different kinds of successes and failures with occurrence probabilities depending on the outcome of the previous trial. This generalization allows a uniform view of occupation time, first passage time and recurrence time. Our results are consequently derived and presented in matrix form, the probabilities as well as the moments. They can be applied to all Discrete Time Markov Chains, especially in computer capacity planning, performability and economics.