It is crucial that ASR systems can handle the wide range of variations in speech of speakers from different demographic groups, with different speaking styles, and of speakers with (dis)abilities. A potential quality-of-service harm arises when ASR systems do not perform equally well for everyone. ASR systems may exhibit bias against certain types of speech, such as non-native accents, different age groups and gender. In this study, we evaluate two widely-used neural network-based architectures: Wav2vec2 and Whisper on potential biases for Dutch speakers. We used the Dutch speech corpus JASMIN as a test set containing read and conversational speech in a human-machine interaction setting. The results reveal a significant bias against non-natives, children and elderly and some regional dialects. The ASR systems generally perform slightly better for women than for men.
MULTIFILE
This paper presents three lesson activities for upper secondary education that focus on learning subject specific knowledge and general system thinking skills by creating a qualitative representation. The learning goals and the pedagogical approach are described.
Introduction: There are good reasons to study urban innovation from a systemic perspective. A key finding in innovation research is that organizations rarely innovate in isolation, but in interaction with clients, competitors, suppliers, and other organizations. A system perspective is useful in understanding and analyzing these interactions. Cities and urban regions are increasingly recognized as key milieus in which these interactions occur. The urban innovation system approach conceptualizes the city or urban region as a context in which innovations emerge from complex interactions between urban actors—firms, citizens, governments, knowledge institutes— in a particular institutional setting. The systemic view of innovation departs from traditional linear models that depict innovation as a staged process that starts with (basic) scientific research and ends with commercialization by companies. Innovation processes are much more complex and diverse, influenced by multiple actors that interact in networks with feedback loops, and involving many types of knowledge beyond scientific knowledge. Urban innovation systems are nested in innovation systems on other spatial levels—regional, national, international. Studies on urban innovation systems seek to explain how innovations emerge in an urban context, why urban regions differ in their innovative performance, and also address questions on the governance and management of such systems. Studies in this field draw from a variety of disciplines including economic geography, urban and regional economics, political sciences, innovation studies, social sciences, and urban planning.
MULTIFILE
