Pasar al contenido principal

SPATIAL AUDIO AND ARRAY PROCESSING FOR INDUSTRIAL APPLICATIONS AND DIGITAL TRANSFORMATION: EFFICIENT IMPLEMENTATIONS THROUGH PARALLEL AND APPROXIMATE COMPUTING

PID2022-137048OA-C43

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2022
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD CARLOS III DE MADRID

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Evaluating and accelerating vision transformers on GPU-based embedded edge AI systems

  • Martin-Salinas, Ignacio
  • Badia, Jose M.
  • Valls, Oscar
  • Leon, German
  • Belloch, Jose A.
  • Amor-Martin, Adrian
  • del Amor, Rocío
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
[EN] Many current embedded systems comprise heterogeneous computing components including quite powerful GPUs, which enables their application across diverse sectors. This study demonstrates the efficient execution of a medium-sized self-supervised audio spectrogram transformer (SSAST) model on a low-power system-on-chip (SoC). Through comprehensive evaluation, including real time inference scenarios, we show that GPUs outperform multi-core CPUs in inference processes. Optimization techniques such as adjusting batch size, model compilation with TensorRT, and reducing data precision significantly enhance inference time, energy consumption, and memory usage. In particular, negligible accuracy degradation is observed, with post-training quantization to 8-bit integers showing less than 1% loss. This research underscores the feasibility of deploying transformer neural networks on low-power embedded devices, ensuring efficiency in time, energy, and memory, while maintaining the accuracy of the results., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work has been supported by the Spanish Ministry of Science and Innovation under projects PID2020-113656RB-C21 and PID2022-137048OA-C43 funded by MCIN/AEI/10.13039/501100011033 and by "ERDF A way of making Europe" as well as TED2021-131401B-C21 and TED2021-131401A-C22.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Urban sound classification using neural networks on embedded FPGAs

  • Belloch, Jose A.
  • Coronado, Raul
  • Valls-Lozano, Óscar
  • León, Germán
  • Dolz, Manuel F.
  • Amor-Martin, Adrian
  • del Amor, Rocío
  • Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
  • Piñero, Gema|||0000-0002-8719-8106
[EN] 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., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work has been funded by the NextGenerationEU/PRTR, MCIN/AEI/10.13039/501100011033 and ERDF A way of making Europe through Grants PID2020-113656RB, PID2021-124280OB-C21, PID2022-137048OA-C43, TED2021-131401B-C21 (DIPSY-AI), and TED2021-131401A-C22 (DIPSYTECH), and by CM through PROGRAMA MIMACUHSPACE-CM-UC3M. G. Piñero and V. Naranjo s work has been partially funded by GVA through PROGRAMA PROMETEO 2023-CIPROM/2022/20. Manuel F. Dolz was also supported by the Plan Gen T grant CIDEXG/2022/013 of the Generalitat Valenciana.