Urban sound classification using neural networks on embedded FPGAs
View/ Open
Impact
Scholar |
Other documents of the author: BELLOCH, JOSE A.; Coronado, Raul; Valls, Oscar; Amor, Rocío del; Leon, German; Naranjo, Valery; Dolz, Manuel F.; Amor-Martin, Adrian; Piñero, Gema
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
Urban sound classification using neural networks on embedded FPGAsAuthor (s)
Date
2024-03-01Publisher
SpringerISSN
0920-8542; 1573-0484Bibliographic citation
Belloch, J.A., Coronado, R., Valls, O. et al. Urban sound classification using neural networks on embedded FPGAs. J Supercomput 80, 13176–13186 (2024). https://doi.org/10.1007/s11227-024-05947-8Type
info:eu-repo/semantics/articleVersion
info:eu-repo/semantics/publishedVersionSubject
Abstract
Sound classification using neural networks has recently produced very accurate results. A large number of different applications use this type of sound classifiers such as controlling and monitoring the type of activity ... [+]
Sound classification using neural networks has recently produced very accurate results. A large number of different applications use this type of sound classifiers such as controlling and monitoring the type of activity in a city or identifying different types of animals in natural environments. While traditional acoustic processing applications have been developed on high-performance computing platforms equipped with expensive multi-channel audio interfaces, the Internet of Things (IoT) paradigm requires the use of more flexible and energy-efficient systems. Although software-based platforms exist for implementing general-purpose neural networks, they are not optimized for sound classification, wasting energy and computational resources. In this work, we have used FPGAs to develop an ad hoc system where only the hardware needed for our application is synthesized, resulting in faster and more energy-efficient circuits. The results show that our developments are accelerated by a factor of 35 compared to a software-based implementation on a Raspberry Pi. [-]
Is part of
The Journal of Supercomputing (2024) 80:13176–13186Related data
No additional data or materials available.Funder Name
NextGenerationEU/PRTR | MCIN/AEI/10.13039/501100011033 | PROGRAMA MIMACUHSPACE-CM-UC3M | Generalitat Valenciana
Project code
PID2020-113656RB | PID2021-124280OB-C21 | TED2021-131401B-C21 (DIPSY-AI) | TED2021-131401A-C22 (DIPSYTECH) | PID2022-137048OA-C43 | 2023-CIPROM/2022/20 | CIDEXG/2022/013
Rights
© The Author(s) 2024
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
This item appears in the folowing collection(s)
- ICC_Articles [430]