(Proceedings of Mensch und Computer 2024, 2024) Schmalfuß-Schwarz, Jan; Gollasch, David; Engel, Christin; Branig, Meinhardt; Weber, Gerhard
This paper explores the personalization of wake words in Active Noise Cancelling (ANC) enabled headphones designed as assistive technology for noise-sensitive individuals. We focus on the incorporation and assessment of intended wake words, categorizing them based on fillers and first names. Given the language-dependent nature of this approach, our research primarily addresses the English language. We propose an evaluation mechanism to determine the efficacy of potential wake words, predicting their recognition accuracy and length. The study involves a comparative analysis between combinations of fillers and first names, aiming to identify the optimal pairing. We offer recommendations on the best-performing combinations, enhancing the reliability and user experience of ANC headphones as a supportive tool for noise-sensitive individuals. Our findings aim to provide a robust framework for developing highly responsive and personalized wake word systems, tailored to the unique needs of noise-sensitive individuals in office environments.