ICT Dissertation Award 2019
Two first prize winners for the first time
This year's presentation of the ICT Dissertation Awards of the Fraunhofer Group for IUK Technology was a premiere: For the first time, the jury found two works worthy of first prize.
The first prize was shared by Dr. Anna-Marie Kruspe from the Fraunhofer Institute for Digital Media Technology in Ilmenau and Dr. Erion Elmasllari from the Fraunhofer Institute for Applied Information Technology in Sankt Augustin.
Anna-Marie Kruspe was awarded for her work "Application of Automatic Speech Recognition Technologies to Singing". The field of music information retrieval deals with the automatic analysis of musical characteristics. One aspect that has hardly been researched so far is the sung text. In automatic speech recognition, many methods are developed for the automatic analysis of speech, but rarely for singing. Anna-Marie Kruspe’s work investigates the application of speech recognition methods to singing and describes ways of applying and improving automatic speech recognition techniques to various vocal search tasks, including phoneme recognition, speech recognition, keyword search, text-to-song approximation, and lyric search. To this end, it pursued two general approaches: First, she works on better phoneme recognition models, which she identified as a general bottleneck in almost all of the above-mentioned retrieval tasks, and trains them with extended voice recordings that are more “songlike” or with real vocal recordings with automatically aligned textual lyrics. Secondly, she adapts the automatic speech recognition techniques to singing, incorporates domain knowledge and makes them more robust to the different characteristics of these data.
With his dissertation "A Framework for the Successful Design and Deployment of Electronic Triage Systems", Erion Elmasllari was able to convince the jury. Triage is the process by which emergency responders, especially when there is a high volume of patients, determine the order and priority of medical assistance. After assessing the severity of the injuries, first responders mark the victims to indicate a treatment priority. At the end of the triage process, victims are treated according to their assigned priority. Erion Elmasllari’s work identifies the key factors determining the acceptance of e-Triage systems and uses them as the basis for a framework for designing such systems. The framework can be used evaluatively to explain the reasons why previous e-Triage systems have failed, but can also be used generatively to actively support system designers in designing accepted e-Triage systems. In both cases, the Framework examines the needs, limitations, risks, and issues of e-Triage systems within the overall triage ecosystem.
The third prize went out to Naser Damer from the Fraunhofer Institute for Computer Graphics Research in Darmstadt for his doctoral thesis entitled "Application-driven Advances in Multi-biometric Fusion". Biometrics is the automated recognition of individuals based on their behaviour or biological characteristics. Typical applications are fingerprint or facial image recognition to gain access to IT systems or rooms. The great advantage of biometrics is that the user does not have to memorize a password or carry a key. In order to create a system that is as secure as possible, numerous approaches are proposed that seek a balance between, for example, security, accuracy and user-friendliness.
A relatively new and promising approach is multibiometric fusion. Here several biometric features are used to identify a particular user. Naser Damer’s work focuses on such multibiometric fusion systems with the aim of improving overall performance and functionality. With the optimization of the fusion process, his approaches achieve higher biometric accuracy through the use of additional information. In addition, he presents specific applications that complement biometric systems and use multibiometric fusion to enhance performance.