CASE: CNN Acceleration for Speech-Classification in Edge-Computing

Haris Gulzar, Muhammad Shakeel, Kenji Nishida, Katsutoshi Itoyama, Kazuhiro Nakadai, Hideharu Amano

研究成果: Conference contribution

抄録

High performance of Machine Learning algorithms has enabled numerous applications based upon speech interface in our daily life, but most of the frameworks use computationally expensive algorithms deployed on cloud servers as speech recognition engines. With the recent surge in the number of IoT devices, a robust and scalable solution for enabling AI applications on IoT devices is inevitable in form of edge computing. In this paper, we propose the application of Systemon-Chip (SoC) powered edge computing device as accelerator for speech commands classification using Convolutional Neural Network (CNN). Different aspects affecting the CNN performance are explored and an efficient and light-weight model named as CASENet is proposed which achieves state-of-the-art performance with significantly smaller number of parameters and operations. Efficient extraction of useful features from audio signal helped to maintain high accuracy with a 6X smaller number of parameters, making CASENet the smallest CNN in comparison to similarly performing networks. Light-weight nature of the model has led to achieve 96.45% validation accuracy with a 14X smaller number of operations which makes it ideal for low-power IoT and edge devices. A CNN accelerator is designed and deployed on FPGA part of SoC equipped edge server device. The hardware accelerator helped to improve the inference latency of speech command by a 6.7X factor as compared to standard implementation. Memory, computational cost and latency are the most important metrics for selecting a model to deploy on edge computing devices, and CASENet along with the accelerator surpasses all of these requirements.

本文言語English
ホスト出版物のタイトルProceedings - 2021 IEEE Cloud Summit, Cloud Summit 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ページ63-68
ページ数6
ISBN(電子版)9781665425827
DOI
出版ステータスPublished - 2021
イベント2021 IEEE Cloud Summit, Cloud Summit 2021 - Virtual, Online, United States
継続期間: 2021 10月 212021 10月 22

出版物シリーズ

名前Proceedings - 2021 IEEE Cloud Summit, Cloud Summit 2021

Conference

Conference2021 IEEE Cloud Summit, Cloud Summit 2021
国/地域United States
CityVirtual, Online
Period21/10/2121/10/22

ASJC Scopus subject areas

  • コンピュータ ネットワークおよび通信
  • コンピュータ サイエンスの応用
  • 制御と最適化
  • 情報システムおよび情報管理

フィンガープリント

「CASE: CNN Acceleration for Speech-Classification in Edge-Computing」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル