Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition

Young Min Lee; Joon Sung Yang

doi:10.1145/3349569.3351534

Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition

Young Min Lee, Joon Sung Yang

College of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Speech recognition technology combined with artificial intelligence represents a quantum leap more accurate than past pattern recognition methods. And server-based system support for scalability, virtualization and huge amounts of unlimited storage resources that greatly contributed to the improvement of the accuracy of its prediction. However, the implementation of server-oriented reforms led to enormous latency and connectivity problems. Therefore, we propose a novel client-edge speech recognition system to enhance latency by using what we call semi-offloading technology. This proposal is promising big performance gains by offloading computing power-dependent tasks to edge nodes and processing throughput-dependent tasks by a client. The merit of semi-offloading as well as a division of workload allows for parallelism and re-ordering among the process. The experimental results show that, 23%∼62% improvement in response time.

Original language	English
Title of host publication	Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450369251
DOIs	https://doi.org/10.1145/3349569.3351534
Publication status	Published - 2019 Oct 13
Event	2019 International Conference on Compliers, Architectures and Synthesis for Embedded Systems, CASES 2019 - New York, United States Duration: 2019 Oct 13 → 2019 Oct 18

Publication series

Name	Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019

Conference

Conference	2019 International Conference on Compliers, Architectures and Synthesis for Embedded Systems, CASES 2019
Country/Territory	United States
City	New York
Period	19/10/13 → 19/10/18

Bibliographical note

Funding Information:
This work was supported in part by the Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019−0−00421, AI Graduate School Support Program), and in part by the Basic Science Research Program through the National Research Foundation of Korea by the Ministry of Education under Grant NRF−2018R1D1A1B07049842.

Publisher Copyright:
© 2019 Association for Computing Machinery.

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Control and Optimization

Access to Document

10.1145/3349569.3351534

Cite this

Lee, Y. M., & Yang, J. S. (2019). Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition. In Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019 [a1] (Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019). Association for Computing Machinery, Inc. https://doi.org/10.1145/3349569.3351534

Lee, Young Min ; Yang, Joon Sung. / Work-in-progress : Computation offloading of acoustic model for client-edge-based speech-recognition. Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019. Association for Computing Machinery, Inc, 2019. (Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019).

@inproceedings{d03b0b8187be4df784256d1454e8ca3d,

title = "Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition",

abstract = "Speech recognition technology combined with artificial intelligence represents a quantum leap more accurate than past pattern recognition methods. And server-based system support for scalability, virtualization and huge amounts of unlimited storage resources that greatly contributed to the improvement of the accuracy of its prediction. However, the implementation of server-oriented reforms led to enormous latency and connectivity problems. Therefore, we propose a novel client-edge speech recognition system to enhance latency by using what we call semi-offloading technology. This proposal is promising big performance gains by offloading computing power-dependent tasks to edge nodes and processing throughput-dependent tasks by a client. The merit of semi-offloading as well as a division of workload allows for parallelism and re-ordering among the process. The experimental results show that, 23%∼62% improvement in response time.",

author = "Lee, {Young Min} and Yang, {Joon Sung}",

note = "Funding Information: This work was supported in part by the Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019−0−00421, AI Graduate School Support Program), and in part by the Basic Science Research Program through the National Research Foundation of Korea by the Ministry of Education under Grant NRF−2018R1D1A1B07049842. Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 2019 International Conference on Compliers, Architectures and Synthesis for Embedded Systems, CASES 2019 ; Conference date: 13-10-2019 Through 18-10-2019",

year = "2019",

month = oct,

day = "13",

doi = "10.1145/3349569.3351534",

language = "English",

series = "Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019",

publisher = "Association for Computing Machinery, Inc",

booktitle = "Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019",

}

Lee, YM & Yang, JS 2019, Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition. in Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019., a1, Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019, Association for Computing Machinery, Inc, 2019 International Conference on Compliers, Architectures and Synthesis for Embedded Systems, CASES 2019, New York, United States, 19/10/13. https://doi.org/10.1145/3349569.3351534

Work-in-progress : Computation offloading of acoustic model for client-edge-based speech-recognition. / Lee, Young Min; Yang, Joon Sung.

Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019. Association for Computing Machinery, Inc, 2019. a1 (Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Work-in-progress

T2 - 2019 International Conference on Compliers, Architectures and Synthesis for Embedded Systems, CASES 2019

AU - Lee, Young Min

AU - Yang, Joon Sung

N1 - Funding Information: This work was supported in part by the Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2019−0−00421, AI Graduate School Support Program), and in part by the Basic Science Research Program through the National Research Foundation of Korea by the Ministry of Education under Grant NRF−2018R1D1A1B07049842. Publisher Copyright: © 2019 Association for Computing Machinery.

PY - 2019/10/13

Y1 - 2019/10/13

N2 - Speech recognition technology combined with artificial intelligence represents a quantum leap more accurate than past pattern recognition methods. And server-based system support for scalability, virtualization and huge amounts of unlimited storage resources that greatly contributed to the improvement of the accuracy of its prediction. However, the implementation of server-oriented reforms led to enormous latency and connectivity problems. Therefore, we propose a novel client-edge speech recognition system to enhance latency by using what we call semi-offloading technology. This proposal is promising big performance gains by offloading computing power-dependent tasks to edge nodes and processing throughput-dependent tasks by a client. The merit of semi-offloading as well as a division of workload allows for parallelism and re-ordering among the process. The experimental results show that, 23%∼62% improvement in response time.

AB - Speech recognition technology combined with artificial intelligence represents a quantum leap more accurate than past pattern recognition methods. And server-based system support for scalability, virtualization and huge amounts of unlimited storage resources that greatly contributed to the improvement of the accuracy of its prediction. However, the implementation of server-oriented reforms led to enormous latency and connectivity problems. Therefore, we propose a novel client-edge speech recognition system to enhance latency by using what we call semi-offloading technology. This proposal is promising big performance gains by offloading computing power-dependent tasks to edge nodes and processing throughput-dependent tasks by a client. The merit of semi-offloading as well as a division of workload allows for parallelism and re-ordering among the process. The experimental results show that, 23%∼62% improvement in response time.

UR - http://www.scopus.com/inward/record.url?scp=85077318966&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077318966&partnerID=8YFLogxK

U2 - 10.1145/3349569.3351534

DO - 10.1145/3349569.3351534

M3 - Conference contribution

AN - SCOPUS:85077318966

T3 - Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019

BT - Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019

PB - Association for Computing Machinery, Inc

Y2 - 13 October 2019 through 18 October 2019

ER -

Lee YM, Yang JS. Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition. In Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019. Association for Computing Machinery, Inc. 2019. a1. (Proceedings of the International Conference on Compliers, Architectures and Synthesis for Embedded Systems Companion, CASES 2019). doi: 10.1145/3349569.3351534

Work-in-progress: Computation offloading of acoustic model for client-edge-based speech-recognition

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this