AudioCAT - competence assessment via voice-controlled computer dialogue systems

Professional language skills are an important basis for effective communication and successful teamwork. The AudioCAT project addresses this by developing an automated process for evaluating language skills.

The AudioCAT system to be developed in the project is intended to help prospective nursing staff and doctors to demonstrate their own professional language skills in realistic situations. The system will provide practical tasks via a screen while at the same time conducting a spontaneous and authentic conversation with the test taker. The specialist knowledge and soft skills are evaluated in the background. The research focus of the project is also on the automatic recognition of non-native English utterances, on intelligent and authentic computer dialogues and on algorithms for evaluating competencies and soft skills such as resilience under stress. Soft skills are important for groups with different native languages and a variety of cultural backgrounds. The competencies of a successful team work are, for example, active listening, experience with handling stress, a solution-oriented approach, decision-making ability and an affinity for transparent communication.

The automated speech recognition technology developed by Fraunhofer IDMT in Oldenburg, which has been integrated into the application can recognise spoken words and sentences. The technology outputs them as text. With the help of the transcribed text, answers are analysed, classified and evaluated on the basis of machine learning methods.

The aim of the project partners is to support staff evaluation in the long term by providing a competence assessment tool for the medical sector. The simulated dialogue with the system can already be tested on the website: www.audiocat.de

The introduction of a computer dialogue system and automated competence testing enables an objective and efficient evaluation of technical and soft skills under realistic conditions and provides a completely new type of competence testing. 

Even though the funding phase has ended, the project partners are continuing to optimise the AudioCAT system.