Abstract
Personal Voice Assistants (PVAs) are used to interact with digital environments and computer systems using speech. A wake word such as ’Alexa’ is spoken by the user to initiate interaction with the PVA. We use the audio recording of the wake word to determine the room in which user - PVA interaction takes place. We collected data from 10 different rooms in which a user speaks the wake word at different lo- cations. This dataset is used to evaluate three different neural network based algorithms for room identification. Our evaluation shows that rooms can be identified with 90% accuracy. The impact is twofold: (i) PVA audio recordings leak private information about the user environment; (ii) Acoustic room identification is an option for augmenting user - PVA interaction.
| Original language | English |
|---|---|
| Title of host publication | EWSN '22 |
| Subtitle of host publication | Proceedings of the 2022 International Conference on Embedded Wireless Systems and Networks |
| Editors | Alois Ferscha, Mun Choon Chan, Salil Kanhere |
| Publisher | Association for Computing Machinery |
| Pages | 262–267 |
| Number of pages | 6 |
| Publication status | Published - 2022 |
| Externally published | Yes |
| Event | Proceedings of the 2022 International Conference on Embedded Wireless Systems and Networks - Linz, Austria Duration: 3 Oct 2022 → 5 Oct 2022 https://dl.acm.org/doi/proceedings/10.5555/3578948 |
Conference
| Conference | Proceedings of the 2022 International Conference on Embedded Wireless Systems and Networks |
|---|---|
| Abbreviated title | EWSN '22 |
| Country/Territory | Austria |
| City | Linz |
| Period | 3/10/22 → 5/10/22 |
| Internet address |
Field of Science*
- 2.2 Electrical engineering, Electronic engineering, Information engineering
Publication Type*
- 3.4. Other publications in conference proceedings (including local)