Johannes Tümler
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Johannes Tümler has a total of 69 co-authors. Here are the top co-authors by number of shared publications:
Anke Huckauf
Ulm University
4 shared publicationsFabian Doil
Volkswagen AG, Germany
3 shared publications- Irina Böckelmann
Institute of Occupational Medicine, Faculty of Medicine, Otto von Guericke University Magdeburg, 39120 Magdeburg, Germany
3 shared publications Lutz Schega
Otto-von-Guericke, University Magdeburg, Germany
3 shared publicationsRüdiger Mecke
Fraunhofer IFF
3 shared publications- Caroline Schon
Department of Electrical, Mechanical and Industrial Engineering, Anhalt University of Applied Sciences, 06366 Köthen (Anhalt), Germany
2 shared publications
Latest Publications
- Open Access
- 13 November 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (22) , 11262
Reliability of Speech Recognition for Conversational Human–Robot Interaction: A Multi-Corpus Analysis of Denoising, Voice Activity Detection, and Transcription
Rising numbers of isolated nursing home residents and nursing staff shortages motivate voice-based conversational assistants for monitoring and companionship; both require reliable transcription without an enrolled speaker profile to reduce staff burden and serve as a baseline for speaker-based methods. We benchmarked a cascaded denoising, voice activity detection (VAD) and speech-to-text pipeline (DeepFilterNet3, Silero VAD, faster-whisper large-v3) at library defaults on five English corpora: utterance-based files (LibriSpeech, AMI clips on digital silence, LibriMix mixtures) and real recordings (CHiME-6). We report the pooled-count word error rate (WER) with cluster-bootstrap intervals, offline VAD F1 and embedding-based semantic error rate (SER). The best WER ranged from 4% on clean read speech to 68% on the CHiME-6 close-talk channel, whose reference omits other participants’ speech. External=VAD routing lowered WER in all 10 matched utterance-based comparisons (0.1 to 5.3 points); on CHiME-6 the effect depended on channel and reference (without denoising: close talk −65.3 points against the wearer’s reference, +12.4 against the all-participants reference; distant array +10.4). Denoising helped substantially only on the CHiME-6 close-talk channel. VAD F1 showed no consistent association with WER on utterance-based files (r = +0.11). The SER misses fluent fabrication. The findings suggest a provisional, in-sample rule needing held-out validation, including older-adult speech.
- 13 November 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (22) , 11262
Open AccessReliability of Speech Recognition for Conversational Human–Robot Interaction: A Multi-Corpus Analysis of Denoising, Voice Activity Detection, and Transcription
Rising numbers of isolated nursing home residents and nursing staff shortages motivate voice-based conversational assistants for monitoring and companionship; both require reliable transcription without an enrolled speaker profile to reduce staff burden and serve as a baseline for speaker-based methods. We benchmarked a cascaded denoising, voice activity detection (VAD) and speech-to-text pipeline (DeepFilterNet3, Silero VAD, faster-whisper large-v3) at library defaults on five English corpora: utterance-based files (LibriSpeech, AMI clips on digital silence, LibriMix mixtures) and real recordings (CHiME-6). We report the pooled-count word error rate (WER) with cluster-bootstrap intervals, offline VAD F1 and embedding-based semantic error rate (SER). The best WER ranged from 4% on clean read speech to 68% on the CHiME-6 close-talk channel, whose reference omits other participants’ speech. External=VAD routing lowered WER in all 10 matched utterance-based comparisons (0.1 to 5.3 points); on CHiME-6 the effect depended on channel and reference (without denoising: close talk −65.3 points against the wearer’s reference, +12.4 against the all-participants reference; distant array +10.4). Denoising helped substantially only on the CHiME-6 close-talk channel. VAD F1 showed no consistent association with WER on utterance-based files (r = +0.11). The SER misses fluent fabrication. The findings suggest a provisional, in-sample rule needing held-out validation, including older-adult speech.
- Open Access
- 1 October 2026
- Published by MDPI AG in Education Sciences
- Vol. 16 (10) , 1622
An Integrative Assessment Framework for Virtual and Augmented Reality in Educational Settings
The use of virtual and augmented reality (xR) in educational contexts opens up new pedagogical possibilities, but places high demands on planning, technology, and ethical responsibility. To date, no systematic tool is available to help educators and decision-makers evaluate use cases of immersive technologies in a structured manner. This article presents the EDU-xR Fit, an integrative evaluation framework that analyzes the use of xR scenarios across the core areas of pedagogical-didactic adaption and fields of action, as well as technical and contextual levels. The framework was developed through a multiphase exploratory design combining qualitative framework development with a supplementary quantitative persona-based weighting phase. The model also incorporates overarching factors such as appropriateness and ethical safeguards. In a web-based tool, key criteria are evaluated using a five-point Likert scale and linked to practical decision-making aids. The framework is proposed as a preliminary decision-support resource for educators and institutions involved in planning, assessing, and reflecting on xR applications. Given its exploratory development and limited practical evaluation, its applicability to institutional decision-making requires further empirical validation. It is designed to promote a reflective and pedagogically grounded use of xR that is tailored to the specific subject, target group, and institutional context.
- 1 October 2026
- Published by MDPI AG in Education Sciences
- Vol. 16 (10) , 1622
Open AccessAn Integrative Assessment Framework for Virtual and Augmented Reality in Educational Settings
The use of virtual and augmented reality (xR) in educational contexts opens up new pedagogical possibilities, but places high demands on planning, technology, and ethical responsibility. To date, no systematic tool is available to help educators and decision-makers evaluate use cases of immersive technologies in a structured manner. This article presents the EDU-xR Fit, an integrative evaluation framework that analyzes the use of xR scenarios across the core areas of pedagogical-didactic adaption and fields of action, as well as technical and contextual levels. The framework was developed through a multiphase exploratory design combining qualitative framework development with a supplementary quantitative persona-based weighting phase. The model also incorporates overarching factors such as appropriateness and ethical safeguards. In a web-based tool, key criteria are evaluated using a five-point Likert scale and linked to practical decision-making aids. The framework is proposed as a preliminary decision-support resource for educators and institutions involved in planning, assessing, and reflecting on xR applications. Given its exploratory development and limited practical evaluation, its applicability to institutional decision-making requires further empirical validation. It is designed to promote a reflective and pedagogically grounded use of xR that is tailored to the specific subject, target group, and institutional context.
- Open Access
- 3 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8785
Decision-Making in Augmented Reality: A Drift Diffusion Analysis of the Effects of Visualization and Hardware
Augmented Reality (AR) is increasingly applied in real-world contexts that requires users to interpret visual information and make rapid decisions. However, little is known about how different AR visualization formats and hardware configurations influence underlying perceptual decision processes. This study addresses how AR-specific technical characteristics affect decision processes in a random-dot motion discrimination task, in which participants discriminate the coherent motion direction of a proportion of dots embedded in random noise, under multiple AR conditions and a real-world baseline condition. Behavioral data were analyzed using the drift-diffusion model to estimate latent decision parameters such as evidence accumulation and decision caution. The results show significant differences between AR configurations, indicating that visualization design and hardware characteristics likely affect the efficiency of evidence processing.
- 3 September 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (17) , 8785
Open AccessDecision-Making in Augmented Reality: A Drift Diffusion Analysis of the Effects of Visualization and Hardware
Augmented Reality (AR) is increasingly applied in real-world contexts that requires users to interpret visual information and make rapid decisions. However, little is known about how different AR visualization formats and hardware configurations influence underlying perceptual decision processes. This study addresses how AR-specific technical characteristics affect decision processes in a random-dot motion discrimination task, in which participants discriminate the coherent motion direction of a proportion of dots embedded in random noise, under multiple AR conditions and a real-world baseline condition. Behavioral data were analyzed using the drift-diffusion model to estimate latent decision parameters such as evidence accumulation and decision caution. The results show significant differences between AR configurations, indicating that visualization design and hardware characteristics likely affect the efficiency of evidence processing.
- Open Access
Evaluation of SiL Testing Potential—Shifting from HiL by Identifying Compatible Requirements with vECUs
Due to the increasing complexity of vehicle software, it is becoming increasingly difficult to comprehensively test all requirements. This inevitably means that alternative test methods, e.g., simulation-based methods, must be used more frequently. However, the challenge involves identifying appropriate requirements that can be technically tested in a simulation environment initially. The present work is aimed at evaluation and optimization of the effectiveness of software-in-the-loop (SiL) simulations in the testing process of vehicle software. The focus is on supporting the testing process by shifting specific test cases from hardware-in-the-loop (HiL) test benches to SiL-based simulations. For this purpose, a systematic approach was developed to analyze and categorize requirements, enabling precise and efficient allocation of test cases. Furthermore, a detailed review and recommendation for improving the ProSTEP iViP standard for virtual electronic control units (vECU) was carried out. The developed matrix associates the defined requirement clusters with different classifications of vECUs, facilitating the identification of suitable test environment types for conducting specific test cases. By assigning test cases to appropriate vECU levels, the testing processes can be targeted and cost-optimized. Finally, the theoretical results were evaluated in an SiL simulation environment. It was observed that a significant part of the requirements could effectively be tested using a vECU. These findings confirmed the potential of SiL simulation environments to not only support, but also enhance, the testing process for vehicle software by providing a cost-effective and flexible complement to traditional HiL test benches.
Open AccessEvaluation of SiL Testing Potential—Shifting from HiL by Identifying Compatible Requirements with vECUs
Due to the increasing complexity of vehicle software, it is becoming increasingly difficult to comprehensively test all requirements. This inevitably means that alternative test methods, e.g., simulation-based methods, must be used more frequently. However, the challenge involves identifying appropriate requirements that can be technically tested in a simulation environment initially. The present work is aimed at evaluation and optimization of the effectiveness of software-in-the-loop (SiL) simulations in the testing process of vehicle software. The focus is on supporting the testing process by shifting specific test cases from hardware-in-the-loop (HiL) test benches to SiL-based simulations. For this purpose, a systematic approach was developed to analyze and categorize requirements, enabling precise and efficient allocation of test cases. Furthermore, a detailed review and recommendation for improving the ProSTEP iViP standard for virtual electronic control units (vECU) was carried out. The developed matrix associates the defined requirement clusters with different classifications of vECUs, facilitating the identification of suitable test environment types for conducting specific test cases. By assigning test cases to appropriate vECU levels, the testing processes can be targeted and cost-optimized. Finally, the theoretical results were evaluated in an SiL simulation environment. It was observed that a significant part of the requirements could effectively be tested using a vECU. These findings confirmed the potential of SiL simulation environments to not only support, but also enhance, the testing process for vehicle software by providing a cost-effective and flexible complement to traditional HiL test benches.
- 16 June 2022
- Published by Springer Nature
- p. 74-93
Multi-user Multi-platform xR Collaboration: System and Evaluation
- 16 June 2022
- Published by Springer Nature
- p. 74-93
Multi-user Multi-platform xR Collaboration: System and Evaluation
- 16 June 2022
- Published by Springer Nature
- p. 224-237
Is Off-the-Shelf VR Software Ready for Medical Teaching?
- 16 June 2022
- Published by Springer Nature
- p. 224-237
Is Off-the-Shelf VR Software Ready for Medical Teaching?
- 16 June 2022
- Published by Springer Nature
- p. 3-20
How to Support Rapid Prototyping of Virtual Content for Automotive AR Head-Up Displays?
- 16 June 2022
- Published by Springer Nature
- p. 3-20
How to Support Rapid Prototyping of Virtual Content for Automotive AR Head-Up Displays?
- 3 July 2021
- Published by Springer Nature
- p. 288-300
Simulation of the Field of View in AR and VR Headsets
- 3 July 2021
- Published by Springer Nature
- p. 288-300
Simulation of the Field of View in AR and VR Headsets
- 5 December 2017
- Published by Springer Nature
- p. 471-483
Investigation of an Augmented Reality-Based Machine Operator Assistance-System
- 5 December 2017
- Published by Springer Nature
- p. 471-483
Investigation of an Augmented Reality-Based Machine Operator Assistance-System