Projects per year
Abstract
Voice is a convenient and popular way to interact with our dig-
ital world. Besides translating speech to text, it is also possible
to identify speakers based on their voice profile. To date, speaker
identification has predominantly been limited to high-performance
computational platforms owing to the intricate nature of the under-
lying algorithms. In this work, we demonstrate that it is possible to
reduce model complexity by the required factor of ∼10, such that
speaker identification can be made feasible for embedded devices
with limited resources. We further describe and discuss novel use
cases, such as voice-based presence detection and authentication,
that become feasible on these class of devices.
ital world. Besides translating speech to text, it is also possible
to identify speakers based on their voice profile. To date, speaker
identification has predominantly been limited to high-performance
computational platforms owing to the intricate nature of the under-
lying algorithms. In this work, we demonstrate that it is possible to
reduce model complexity by the required factor of ∼10, such that
speaker identification can be made feasible for embedded devices
with limited resources. We further describe and discuss novel use
cases, such as voice-based presence detection and authentication,
that become feasible on these class of devices.
| Original language | English |
|---|---|
| Publication status | Accepted/In press - 26 Sept 2023 |
| Event | 21st ACM Conference on Embedded Networked Sensor Systems: SenSys 2023 - Bahcesehir University, Istanbul, Turkey Duration: 13 Nov 2023 → 15 Nov 2023 https://sensys.acm.org/2023/ |
Conference
| Conference | 21st ACM Conference on Embedded Networked Sensor Systems |
|---|---|
| Abbreviated title | SenSys |
| Country/Territory | Turkey |
| City | Istanbul |
| Period | 13/11/23 → 15/11/23 |
| Internet address |
Fields of Expertise
- Information, Communication & Computing
Fingerprint
Dive into the research topics of 'Poster Abstract: Towards Speaker Identification on Resource-Constrained Embedded Devices'. Together they form a unique fingerprint.Projects
- 2 Active
-
SPiDR - Secure, Performant, Dependable, and Resilient Wireless Mesh Networks
Römer, K. U., Schuß, M., Boano, C. A., Gallacher, M., Schuh, M. P. & Basic, F.
1/07/21 → 31/12/24
Project: Research project
-
Intelligent & Networked Embedded Systems
Boano, C. A., Römer, K. U., Schuß, M., Cao, N., Saukh, O., Hofmann, R., Stocker, M., Schuh, M. P., Papst, F., Salomon, E., Brunner, H., Gallacher, M., Mohamed Hydher, M. H., Wang, D., Corti, F., Krisper, M., Basic, F. & Petrovic, K.
1/09/13 → 31/12/24
Project: Research area
Prizes
-
Best poster runner-up for "Towards Speaker Identification on Resource-Constrained Embedded Devices"
Gallacher, Markus (Recipient), Boano, Carlo Alberto (Recipient), Sankar, M.S. Arun (Recipient), Roedig, Utz (Recipient), Lunardi, Willian T. (Recipient) & Baddeley, Michael (Recipient), 15 Nov 2023
Prize: Prizes / Medals / Awards