Oliver Jokisch
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
Oliver Jokisch has a total of 74 co-authors. Here are the top co-authors by number of shared publications:
Rüdiger Hoffmann
TU Dresden
6 shared publications- Hongwei Ding
Speech-Language-Hearing Center, School of Foreign Languages, Shanghai Jiao Tong University, China
4 shared publications - Gunnar Auth
Hochschule Meißen, Meißen, Deutschland
3 shared publications Michael Maruschke
3 shared publicationsRudiger Hoffmann
Dresden University of Technology, Chair of System Theory and Speech Technology Helmholtz Street 18, 01069 Dresden, Germany
3 shared publications- Alexander Leipnitz
Leipzig University of Telecommunications (HfTL), Germany
2 shared publications
Latest Publications
- Open Access
- 28 September 2023
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 11 (1) , 1-13
A systematic mapping study of standards and frameworks for information management in the digital era
The close links of Information Management (IM) and Information Technology (IT) create an evolving environment of tasks and processes. Management standards are normative descriptions of an agreed-upon set of management tasks and suggested ways of task execution. Certain standards like ITIL and COBIT (both used as a brand only by the owners, Axelos and ISACA respectively) have been popular for a long time in sub-areas of IM including IT governance, IT service management, or IT project management. Driven by digitalization, the number and update frequency of IM-related standards have significantly increased recently, making standard selection and implementation more difficult. This study presents a systematic mapping of the current state of IM standardization with respect to standardization bodies, types of standards, and certifications. Visual maps provide an overview of the IM standard landscape and reveal relevant topics and other categories. The article identifies the most relevant standardization bodies, standard types, and topics of the IM domain based on a full set of 109 IM standards. As a mapping outcome, the correlations of standardization bodies versus standard types, and of the topics versus IM task areas are clearly arranged in diagrams.
- 28 September 2023
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 11 (1) , 1-13
Open AccessA systematic mapping study of standards and frameworks for information management in the digital era
The close links of Information Management (IM) and Information Technology (IT) create an evolving environment of tasks and processes. Management standards are normative descriptions of an agreed-upon set of management tasks and suggested ways of task execution. Certain standards like ITIL and COBIT (both used as a brand only by the owners, Axelos and ISACA respectively) have been popular for a long time in sub-areas of IM including IT governance, IT service management, or IT project management. Driven by digitalization, the number and update frequency of IM-related standards have significantly increased recently, making standard selection and implementation more difficult. This study presents a systematic mapping of the current state of IM standardization with respect to standardization bodies, types of standards, and certifications. Visual maps provide an overview of the IM standard landscape and reveal relevant topics and other categories. The article identifies the most relevant standardization bodies, standard types, and topics of the IM domain based on a full set of 109 IM standards. As a mapping outcome, the correlations of standardization bodies versus standard types, and of the topics versus IM task areas are clearly arranged in diagrams.
- Open Access
- 24 July 2021
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 9 (1) , 1-15
A cross-language study of speech recognition systems for English, German, and Hebrew
Despite the growing importance of Automatic Speech Recognition (ASR), its application is still challenging, limited, language-dependent, and requires considerable resources. The resources required for ASR are not only technical, they also need to reflect technological trends and cultural diversity. The purpose of this research is to explore ASR performance gaps by a comparative study of American English, German, and Hebrew. Apart from different languages, we also investigate different speaking styles – utterances from spontaneous dialogues and utterances from frontal lectures (TED-like genre). The analysis includes a comparison of the performance of four ASR engines (Google Cloud, Google Search, IBM Watson, and WIT.ai) using four commonly used metrics: Word Error Rate (WER); Character Error Rate (CER); Word Information Lost (WIL); and Match Error Rate (MER). As expected, findings suggest that English ASR systems provide the best results. Contrary to our hypothesis regarding ASR’s low performance for under-resourced languages, we found that the Hebrew and German ASR systems have similar performance. Overall, our findings suggest that ASR performance is language-dependent and system-dependent. Furthermore, ASR may be genre-sensitive, as our results showed for German. This research contributes a valuable insight for improving ubiquitous global consumption and management of knowledge and calls for corporate social responsibility of commercial companies, to develop ASR under Fair, Reasonable, and Non-Discriminatory (FRAND) terms
- 24 July 2021
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 9 (1) , 1-15
Open AccessA cross-language study of speech recognition systems for English, German, and Hebrew
Despite the growing importance of Automatic Speech Recognition (ASR), its application is still challenging, limited, language-dependent, and requires considerable resources. The resources required for ASR are not only technical, they also need to reflect technological trends and cultural diversity. The purpose of this research is to explore ASR performance gaps by a comparative study of American English, German, and Hebrew. Apart from different languages, we also investigate different speaking styles – utterances from spontaneous dialogues and utterances from frontal lectures (TED-like genre). The analysis includes a comparison of the performance of four ASR engines (Google Cloud, Google Search, IBM Watson, and WIT.ai) using four commonly used metrics: Word Error Rate (WER); Character Error Rate (CER); Word Information Lost (WIL); and Match Error Rate (MER). As expected, findings suggest that English ASR systems provide the best results. Contrary to our hypothesis regarding ASR’s low performance for under-resourced languages, we found that the Hebrew and German ASR systems have similar performance. Overall, our findings suggest that ASR performance is language-dependent and system-dependent. Furthermore, ASR may be genre-sensitive, as our results showed for German. This research contributes a valuable insight for improving ubiquitous global consumption and management of knowledge and calls for corporate social responsibility of commercial companies, to develop ASR under Fair, Reasonable, and Non-Discriminatory (FRAND) terms
- Open Access
- 1 September 2020
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 8 (2) , 17-30
Knowledge-based systems for the Configure Price Quote (CPQ) process – A case study in the IT solution business
Software systems for the Configure Price Quote (CPQ) process of complex product portfolios have emerged in the sales function of companies recently. A flexible quote of complex products, in particular for a Business-to-Business (B2B) customer requires a wide variability of product features and configurations, along with the ability to deliver competitive quotes in short time. The CPQ system aims to reduce the process time, to increase the process quality by integrating information and data stored in several enterprise systems with codified explicit and implicit knowledge from individuals. As in most of the knowledge management systems, the openness of the knowledge holders to share and codify their individual knowledge is a critical success factor. In this case study, we look at the CPQ system implementation of a multinational Information Technology (IT) solution provider from a process perspective and with regard to both the technical and organizational challenges in a holistic approach. The article starts with an introduction to CPQ systems based on works from the Knowledge Management (KM) domain. After outlining our research methodology, we present the case together with a generalization of the CPQ implementation process. Our findings from the investigated scenario indicate positive influence of 1) the internal promotion of CPQ systems as technology innovation for motivating expert knowledge holders to collaborate; 2) an active preparation of the organizational environment for the upcoming changes; and 3) a hybrid agile implementation process.
- 1 September 2020
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 8 (2) , 17-30
Open AccessKnowledge-based systems for the Configure Price Quote (CPQ) process – A case study in the IT solution business
Software systems for the Configure Price Quote (CPQ) process of complex product portfolios have emerged in the sales function of companies recently. A flexible quote of complex products, in particular for a Business-to-Business (B2B) customer requires a wide variability of product features and configurations, along with the ability to deliver competitive quotes in short time. The CPQ system aims to reduce the process time, to increase the process quality by integrating information and data stored in several enterprise systems with codified explicit and implicit knowledge from individuals. As in most of the knowledge management systems, the openness of the knowledge holders to share and codify their individual knowledge is a critical success factor. In this case study, we look at the CPQ system implementation of a multinational Information Technology (IT) solution provider from a process perspective and with regard to both the technical and organizational challenges in a holistic approach. The article starts with an introduction to CPQ systems based on works from the Knowledge Management (KM) domain. After outlining our research methodology, we present the case together with a generalization of the CPQ implementation process. Our findings from the investigated scenario indicate positive influence of 1) the internal promotion of CPQ systems as technology innovation for motivating expert knowledge holders to collaborate; 2) an active preparation of the organizational environment for the upcoming changes; and 3) a hybrid agile implementation process.
- Open Access
- 14 June 2020
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 7 (1) , 53-62
The effect of image resolution in the human presence detection: A case study on real-world image data
The automated operation of robots and flying drones is coupled to high security requirements with respect to humans and environment. Sometimes, persons have to be detected from a long distance or high altitude to allow the autonomous system an adequate and timely response. State-of-the-art Convolutional Neural Networks (CNNs) enable high object detection rates for different image data but only within their respective training, validation and test datasets. Recent studies show the limited generalization ability of CNNs for unknown data, even with merely small image changes. A typical source of such problems is the varying resolution of input images and the inevitable scaling of them to match the input-layer size of the network model. While modern cameras are able to capture high-resolution images of humans also from a longer distance, the practical input-layer sizes of networks are comparably small. Hence, we investigate the reliability of a network architecture for human detection with respect to such input-scaling effects. The popular VisDrone dataset with its varying image resolution and many relatively small depictions of humans is surveyed as well as the high-resolution AgriDrone image data from an agricultural context. Our results show that the object detection rate depends on the image scaling factor as well as on the relative size of persons. An enlarged input-layer size of the network can only partially contribute to counteract the observed effects. In addition, the detection algorithm becomes computationally more expensive by the increased effort.
- 14 June 2020
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 7 (1) , 53-62
Open AccessThe effect of image resolution in the human presence detection: A case study on real-world image data
The automated operation of robots and flying drones is coupled to high security requirements with respect to humans and environment. Sometimes, persons have to be detected from a long distance or high altitude to allow the autonomous system an adequate and timely response. State-of-the-art Convolutional Neural Networks (CNNs) enable high object detection rates for different image data but only within their respective training, validation and test datasets. Recent studies show the limited generalization ability of CNNs for unknown data, even with merely small image changes. A typical source of such problems is the varying resolution of input images and the inevitable scaling of them to match the input-layer size of the network model. While modern cameras are able to capture high-resolution images of humans also from a longer distance, the practical input-layer sizes of networks are comparably small. Hence, we investigate the reliability of a network architecture for human detection with respect to such input-scaling effects. The popular VisDrone dataset with its varying image resolution and many relatively small depictions of humans is surveyed as well as the high-resolution AgriDrone image data from an agricultural context. Our results show that the object detection rate depends on the image scaling factor as well as on the relative size of persons. An enlarged input-layer size of the network can only partially contribute to counteract the observed effects. In addition, the detection algorithm becomes computationally more expensive by the increased effort.
- 30 August 2019
- Published by Springer Nature in Smart Innovation, Systems and Technologies
- p. 305-317
A Pilot Study on the Acoustic Signal Processing at a Small Aerial Drone
- 30 August 2019
- Published by Springer Nature in Smart Innovation, Systems and Technologies
- p. 305-317
A Pilot Study on the Acoustic Signal Processing at a Small Aerial Drone
- 24 July 2019
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 64-74
Towards a Dialect Classification in German Speech Samples
- 24 July 2019
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 64-74
Towards a Dialect Classification in German Speech Samples
- 24 July 2019
- Published by Springer Nature
- p. 180-190
Don’t Talk to Noisy Drones – Acoustic Interaction with Unmanned Aerial Vehicles
- 24 July 2019
- Published by Springer Nature
- p. 180-190
Don’t Talk to Noisy Drones – Acoustic Interaction with Unmanned Aerial Vehicles
- Open Access
- 10 April 2019
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 7 (1) , 27-39
Revisiting automated project management in the digital age – a survey of AI approaches
In this decade, remarkable progress has been made in the field of artificial intelligence (AI). Inspired by well-known services of cognitive assistance systems such as IBM Watson, Apple's Siri or Google Duplex, AI concepts and algorithms are widely discussed regarding their automation potentials in business, politics and society. At first glance, project management (PM) seems to be less suitable for automation due to the inherent uniqueness of projects by definition. However, AI is also creating new application possibilities in the PM area, which will be explored in this contribution by involving an extensive literature review as well as real-world examples. The objective of this article is to provide a current overview of AI approaches and available tools that can be used for automating tasks in business project management.
- 10 April 2019
- Published by International Institute for Applied Knowledge Management - IIAKM in Online Journal of Applied Knowledge Management
- Vol. 7 (1) , 27-39
Open AccessRevisiting automated project management in the digital age – a survey of AI approaches
In this decade, remarkable progress has been made in the field of artificial intelligence (AI). Inspired by well-known services of cognitive assistance systems such as IBM Watson, Apple's Siri or Google Duplex, AI concepts and algorithms are widely discussed regarding their automation potentials in business, politics and society. At first glance, project management (PM) seems to be less suitable for automation due to the inherent uniqueness of projects by definition. However, AI is also creating new application possibilities in the PM area, which will be explored in this contribution by involving an extensive literature review as well as real-world examples. The objective of this article is to provide a current overview of AI approaches and available tools that can be used for automating tasks in business project management.
- Open Access
- 1 January 2019
- Published by University of West Bohemia
Performance Assessment of Convolutional Neural Networks for Semantic Image Segmentation
- 1 January 2019
- Published by University of West Bohemia
Open AccessPerformance Assessment of Convolutional Neural Networks for Semantic Image Segmentation
- 25 August 2018
- Published by Springer Nature
- p. 408-418
QuARTCS: A Tool Enabling End-to-Any Speech Quality Assessment of WebRTC-Based Calls
- 25 August 2018
- Published by Springer Nature
- p. 408-418
QuARTCS: A Tool Enabling End-to-Any Speech Quality Assessment of WebRTC-Based Calls