Abstract
This paper proposes a novel binary voice keyword spotting (KWS) architecture that uses wavelet packets to reduce the implementation cost of its feature extraction component. The approach achieves 32% decrease in memory footprint compared to conventional Fourier-based KWS architectures.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 25th International Symposium on Quality Electronic Design, ISQED 2024 |
| ISBN (Electronic) | 9798350309270 |
| DOIs | |
| State | Published - 2024 |
| Event | 25th International Symposium on Quality Electronic Design, ISQED 2024 - Hybrid, San Francisco, United States Duration: Apr 3 2024 → Apr 5 2024 |
Publication series
| Name | Proceedings - International Symposium on Quality Electronic Design, ISQED |
|---|---|
| ISSN (Print) | 1948-3287 |
| ISSN (Electronic) | 1948-3295 |
Conference
| Conference | 25th International Symposium on Quality Electronic Design, ISQED 2024 |
|---|---|
| Country/Territory | United States |
| City | Hybrid, San Francisco |
| Period | 4/3/24 → 4/5/24 |
Bibliographical note
Publisher Copyright:© 2024 IEEE.
ASJC Scopus subject areas
- Hardware and Architecture
- Electrical and Electronic Engineering
- Safety, Risk, Reliability and Quality