Logo des Repositoriums
 
Konferenzbeitrag

Customized Wake-Word Integration in ANC-Enabled Headphones: Enhancing Assistive Technology for Noise-Sensitive Employees in Office

Vorschaubild nicht verfügbar

Volltext URI

Dokumententyp

Text/Conference Paper

Zusatzinformation

Datum

2024

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Verlag

Association for Computing Machinery

Zusammenfassung

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.

Beschreibung

Schmalfuß-Schwarz, Jan; Gollasch, David; Engel, Christin; Branig, Meinhardt; Weber, Gerhard (2024): Customized Wake-Word Integration in ANC-Enabled Headphones: Enhancing Assistive Technology for Noise-Sensitive Employees in Office. Proceedings of Mensch und Computer 2024. DOI: 10.1145/3670653.3677489. Association for Computing Machinery. pp. 533–537. Karlsruhe, Germany

Zitierform

Tags