Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs

In recent years, Environmental Sound Recognition (ESR) has become a relevant capability for urban monitoring applications. The techniques for automated sound recognition often rely on machine learning approaches, which have increased in complexity in order to achieve higher accuracy. Nonetheless, su...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jurgen Vandendriessche, Nick Wouters, Bruno da Silva, Mimoun Lamrini, Mohamed Yassin Chkouri, Abdellah Touhafi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	environmental sound recognition supervised learning neural networks embedded systems FPGA TPU Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/8a47ba5ce0074a80b4514ee2704b523f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8a47ba5ce0074a80b4514ee2704b523f
record_format	dspace
spelling	oai:doaj.org-article:8a47ba5ce0074a80b4514ee2704b523f2021-11-11T15:38:28ZEnvironmental Sound Recognition on Embedded Systems: From FPGAs to TPUs10.3390/electronics102126222079-9292https://doaj.org/article/8a47ba5ce0074a80b4514ee2704b523f2021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2622https://doaj.org/toc/2079-9292In recent years, Environmental Sound Recognition (ESR) has become a relevant capability for urban monitoring applications. The techniques for automated sound recognition often rely on machine learning approaches, which have increased in complexity in order to achieve higher accuracy. Nonetheless, such machine learning techniques often have to be deployed on resource and power-constrained embedded devices, which has become a challenge with the adoption of deep learning approaches based on Convolutional Neural Networks (CNNs). Field-Programmable Gate Arrays (FPGAs) are power efficient and highly suitable for computationally intensive algorithms like CNNs. By fully exploiting their parallel nature, they have the potential to accelerate the inference time as compared to other embedded devices. Similarly, dedicated architectures to accelerate Artificial Intelligence (AI) such as Tensor Processing Units (TPUs) promise to deliver high accuracy while achieving high performance. In this work, we evaluate existing tool flows to deploy CNN models on FPGAs as well as on TPU platforms. We propose and adjust several CNN-based sound classifiers to be embedded on such hardware accelerators. The results demonstrate the maturity of the existing tools and how FPGAs can be exploited to outperform TPUs.Jurgen VandendriesscheNick WoutersBruno da SilvaMimoun LamriniMohamed Yassin ChkouriAbdellah TouhafiMDPI AGarticleenvironmental sound recognitionsupervised learningneural networksembedded systemsFPGATPUElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2622, p 2622 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	environmental sound recognition supervised learning neural networks embedded systems FPGA TPU Electronics TK7800-8360
spellingShingle	environmental sound recognition supervised learning neural networks embedded systems FPGA TPU Electronics TK7800-8360 Jurgen Vandendriessche Nick Wouters Bruno da Silva Mimoun Lamrini Mohamed Yassin Chkouri Abdellah Touhafi Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
description	In recent years, Environmental Sound Recognition (ESR) has become a relevant capability for urban monitoring applications. The techniques for automated sound recognition often rely on machine learning approaches, which have increased in complexity in order to achieve higher accuracy. Nonetheless, such machine learning techniques often have to be deployed on resource and power-constrained embedded devices, which has become a challenge with the adoption of deep learning approaches based on Convolutional Neural Networks (CNNs). Field-Programmable Gate Arrays (FPGAs) are power efficient and highly suitable for computationally intensive algorithms like CNNs. By fully exploiting their parallel nature, they have the potential to accelerate the inference time as compared to other embedded devices. Similarly, dedicated architectures to accelerate Artificial Intelligence (AI) such as Tensor Processing Units (TPUs) promise to deliver high accuracy while achieving high performance. In this work, we evaluate existing tool flows to deploy CNN models on FPGAs as well as on TPU platforms. We propose and adjust several CNN-based sound classifiers to be embedded on such hardware accelerators. The results demonstrate the maturity of the existing tools and how FPGAs can be exploited to outperform TPUs.
format	article
author	Jurgen Vandendriessche Nick Wouters Bruno da Silva Mimoun Lamrini Mohamed Yassin Chkouri Abdellah Touhafi
author_facet	Jurgen Vandendriessche Nick Wouters Bruno da Silva Mimoun Lamrini Mohamed Yassin Chkouri Abdellah Touhafi
author_sort	Jurgen Vandendriessche
title	Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
title_short	Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
title_full	Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
title_fullStr	Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
title_full_unstemmed	Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs
title_sort	environmental sound recognition on embedded systems: from fpgas to tpus
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8a47ba5ce0074a80b4514ee2704b523f
work_keys_str_mv	AT jurgenvandendriessche environmentalsoundrecognitiononembeddedsystemsfromfpgastotpus AT nickwouters environmentalsoundrecognitiononembeddedsystemsfromfpgastotpus AT brunodasilva environmentalsoundrecognitiononembeddedsystemsfromfpgastotpus AT mimounlamrini environmentalsoundrecognitiononembeddedsystemsfromfpgastotpus AT mohamedyassinchkouri environmentalsoundrecognitiononembeddedsystemsfromfpgastotpus AT abdellahtouhafi environmentalsoundrecognitiononembeddedsystemsfromfpgastotpus
_version_	1718434811269349376

Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs

Ejemplares similares