eKidz app implements an integrated learning system with automated evaluation of reading skills using AI
Despite all efforts in recent years, the downward trend in the basic skills of young learners has not been halted.
The Munich-based startup eKidz, together with its partners at Fraunhofer IDMT in Oldenburg, the University of Regensburg and Flensburg University of Applied Sciences, has now completed an innovative solution for use in schools as part of the “LeseKind” (Reading Child) research and development project (Federal Ministry of Education and Research of Germany project code: 01IS22009). The system for reading and language support combines automatic analysis of reading skills with AI, adaptive feedback and a systematic learning program. The program sets in motion an AI-driven cycle of learning, analysis and support that is often too complex and time-consuming for teachers to create on their own in the classroom.
As part of the project, the Fraunhofer Institute for Digital Media Technology IDMT in Oldenburg contributed its automatic speech recognition algorithms for children's speech and jointly with eKidz and partners adapted them specifically for reading aloud. An important project focus of the developers was the applicability of automatic speech recognition for children's speech in a noisy classroom environment, as well as the final integration and evaluation of the assessment algorithms for reading diagnosis. The language analysis is integrated into the eKidz app and is based on both the initial level assignment and the ongoing assessment of learning progress in the context of 12 AI reading fluency tests.
Since October 2024, the final component of the integrated learning system—automated placement into reading levels—has been offered to all users. An AI-supported oral reading fluency assessment is displayed in the eKidz app when the user first logs in, and the automatic scoring is conducted placing a student at an appropriate level of the program. The AI level assignment makes it easier for the child to start learning at the optimal level and for the teacher to provide appropriate support from the very first lesson.
The AI reading fluency tests, which measure reading accuracy, reading speed, and reading comprehension, provide an ongoing reading skills analysis of each child. It automates the formative assessment of reading. Teachers can determine exactly when the ongoing reading assessment is administered to their students with just one click. The necessary kind of support is made visible in the app for individual students, the class, and the entire school.
The eKidz app leads to greater personalization of learning, since the AI reading analysis is carried out at a differentiated level. It addresses the first to six grades of elementary school as well as the language support classes in middle and high school.
The number of tests, which can also be taken several times by a child, allows a more succinct, yet thorough, individual assessment than traditional assessment procedures, which are only carried out once or twice a year, if at all.
The eKidz solution does not require any additional teacher resources, as the data is collected in the eKidz app's program, which has already been tried and tested in schools. This means that the data that is regularly collected during reading classes in the safe environment of the eKidz app is readily available to the teacher. They no longer have to spend time determining the learning status of their students. The AI feature created in this project takes care of assessment, feedback, and progress tracking. The “LeseKind” (Reading Child) project has created a combination of AI-supported automated reading diagnosis and personalized support based on this that is unique in Europe and internationally.
“Compared to conventional reading support programs, the eKidz app enables continuous monitoring of the reading learning process and feedback on learning progress to the children and teachers. This close-meshed feedback is particularly beneficial for learning.” – Dr. Anita Schilcher, professor from the University of Regensburg
“The speed of the analysis and the accuracy of the evaluation increase motivation during learning. The adaptation of our speech recognition technology to the field of reading exercises and children's language is very important for this and has also proven successful in the “LeseKind” (Reading Child) project.” – Jan Wellmann, Group Leader Audio System Technology & Automatic Speech Recognition at Fraunhofer IDMT.
“We can now offer school administrators, involved in learning assessment and individual diagnostics, a sound, state-of-the-art solution. In view of the growing number of students struggling in the core subject of literacy, we can relieve the burden on teachers and make it easier to support young learners. This includes ongoing assessment of the learning situation.” – Nataliya (Natasha) Tetruyeva, founder and CEO of eKidz.
“Automated grading using AI opens up new ways of supporting children in learning to read. It is also highly scalable and offers potential for further research activities in reading support.” – Dr. Peter John, professor from the Flensburg University of Applied Sciences
The international award-winning start-up eKidz was founded in 2017 and is developing an app for teaching children to read and learn languages at school. The AI reading fluency assessment developed as part of the “LeseKind” (Reading Child) research project is incorporated into the eKidz app. To learn more about eKidz's current program, visit www.ekidz.eu.
eKidz provides a personalized learning and reading experience and targeted language development support for primary school students. eKidz facilitates the incorporation and education of multiple language learners who are insecure in a school’s taught language medium. eKidz achieves this by making acquiring literacy and language competencies interactive and accessible for every child. Working in conjunction with teachers, eKidz provides personalized instruction for K-12 students utilizing purpose-built AI speech diagnostics and adaptive feedback. A universal reading and language app, eKidz was designed for self-guided reading practice; for multiple language learners and for interventions and for literacy instruction. Personalized language development is also being used successfully in special education.
Nataliya Tetruyeva, CEO
Tel. +49 89-20940905
info@ekidz.eu
Flensburg University of Applied Sciences is a public university in Schleswig-Holstein. Its teaching and research focuses on the fields of technology, economics, and computer science.
Torsten Haase
https://hs-flensburg.de/hochschule/personen/haase
Founded in 2008 by Prof. Dr. Dr. Birger Kollmeier and Dr. Jens-E. Appell, the Fraunhofer Institute for Digital Media Technology IDMT’s Branch for Hearing, Speech and Audio Technology HSA stands for market-oriented research and development with a focus on the following areas:
With in-house expertise in the development of hardware and software systems for audio system technology and signal enhancement, the employees at the Oldenburg site are responsible for transferring scientific findings into practical, customer-oriented solutions. Through scientific cooperation, the institute is closely linked to the Carl von Ossietzky University, Jade University of Applied Sciences, and the University of Applied Sciences Emden/Leer. Fraunhofer IDMT is a partner in the »Hearing4all« cluster of excellence and in the Collaborative Research Centre »Hearing Acoustics«.
Christian Colmer
Head of Marketing and Communication Oldenburg Branch HSA
Fraunhofer Institute for Digital Media Technology IDMT
Hearing, Speech and Audio Technology HSA
Marie-Curie-Straße 2
26129 Oldenburg, Germany
Tel. +49 441 2172-436
christian.colmer@idmt.fraunhofer.de
http://www.idmt.fraunhofer.de/hsa
The University of Regensburg (UR), founded in 1962, is a modern campus university. As a comprehensive university, it unites twelve faculties on one contiguous campus and has one of the most modern university libraries in Germany. Initially planned as a regional university, in the new millennium it has developed into a renowned, internationally oriented center for research and teaching. Research at the UR is extremely successful in the natural sciences, life sciences, and humanities.
https://www.uni-regensburg.de
Dr. Johannes Wild / Prof. Dr. Anita Schilcher
Presidential Department
Communication & Marketing
Press Officer Bastian Schmidt
Tel. +49 941 943-5566
E-Mail: presse@ur.de