An experiment of dual-LTE MPTCP with In-Car Voice Assistant

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Vu Anh Vu
  • Mark Akselrod
View graph of relations

Details

Original languageEnglish
Title of host publication2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings)
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (electronic)9781728189642
ISBN (print)978-1-7281-8965-9
Publication statusPublished - Apr 2021
Event93rd IEEE Vehicular Technology Conference (VTC 2021-Spring) - Online, Online
Duration: 25 Apr 202128 Apr 2021

Publication series

NameIEEE Vehicular Technology Conference
ISSN (Print)1090-3038
ISSN (electronic)2577-2465

Abstract

The use of voice assistants in vehicles has been increasing drastically in recent years. Most of the current in-car assistants send voice commands to their cloud server to recognize the speech, process the requests, and return responses. Given that the Vehicle-to-Infrastructure connection quality is sufficient, the response times should be negligible, so that users and their assistants can keep a seamless conversation. The vast majority of current in-car systems are using LTE to connect to the Internet, even though not every LTE provider offers good coverage, especially on highways. In this paper, we investigate the use of multiple LTE providers to enhance connection availability and robustness. To combine multiple LTE interfaces into a single connection, we use MPTCP - a TCP extension that enables multi-path transmission. This work evaluates the voice response latency of MPTCP with two well-known schedulers (Lowest-RTT-first and Redundant) and compares them to single LTE configurations in three setups: emulated network, stationary, and in-car mobile measurements.

Keywords

    interactive application, MPTCP, multi-path scheduling, transport protocol, V2I, voice assistant

ASJC Scopus subject areas

Cite this

An experiment of dual-LTE MPTCP with In-Car Voice Assistant. / Vu, Vu Anh; Akselrod, Mark.
2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings). Institute of Electrical and Electronics Engineers Inc., 2021. 9448971 (IEEE Vehicular Technology Conference).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Vu, VA & Akselrod, M 2021, An experiment of dual-LTE MPTCP with In-Car Voice Assistant. in 2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings)., 9448971, IEEE Vehicular Technology Conference, Institute of Electrical and Electronics Engineers Inc., 93rd IEEE Vehicular Technology Conference (VTC 2021-Spring), Online, 25 Apr 2021. https://doi.org/10.1109/VTC2021-Spring51267.2021.9448971
Vu, V. A., & Akselrod, M. (2021). An experiment of dual-LTE MPTCP with In-Car Voice Assistant. In 2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings) Article 9448971 (IEEE Vehicular Technology Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTC2021-Spring51267.2021.9448971
Vu VA, Akselrod M. An experiment of dual-LTE MPTCP with In-Car Voice Assistant. In 2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings). Institute of Electrical and Electronics Engineers Inc. 2021. 9448971. (IEEE Vehicular Technology Conference). doi: 10.1109/VTC2021-Spring51267.2021.9448971
Vu, Vu Anh ; Akselrod, Mark. / An experiment of dual-LTE MPTCP with In-Car Voice Assistant. 2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings). Institute of Electrical and Electronics Engineers Inc., 2021. (IEEE Vehicular Technology Conference).
Download
@inproceedings{f0e1cd829dff4c3b8d852a139d63dd8e,
title = "An experiment of dual-LTE MPTCP with In-Car Voice Assistant",
abstract = "The use of voice assistants in vehicles has been increasing drastically in recent years. Most of the current in-car assistants send voice commands to their cloud server to recognize the speech, process the requests, and return responses. Given that the Vehicle-to-Infrastructure connection quality is sufficient, the response times should be negligible, so that users and their assistants can keep a seamless conversation. The vast majority of current in-car systems are using LTE to connect to the Internet, even though not every LTE provider offers good coverage, especially on highways. In this paper, we investigate the use of multiple LTE providers to enhance connection availability and robustness. To combine multiple LTE interfaces into a single connection, we use MPTCP - a TCP extension that enables multi-path transmission. This work evaluates the voice response latency of MPTCP with two well-known schedulers (Lowest-RTT-first and Redundant) and compares them to single LTE configurations in three setups: emulated network, stationary, and in-car mobile measurements.",
keywords = "interactive application, MPTCP, multi-path scheduling, transport protocol, V2I, voice assistant",
author = "Vu, {Vu Anh} and Mark Akselrod",
note = "Funding Information: Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 227198829 / GRK1931 SocialCars.; 93rd IEEE Vehicular Technology Conference (VTC 2021-Spring), VTC 2021-Spring ; Conference date: 25-04-2021 Through 28-04-2021",
year = "2021",
month = apr,
doi = "10.1109/VTC2021-Spring51267.2021.9448971",
language = "English",
isbn = "978-1-7281-8965-9",
series = "IEEE Vehicular Technology Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings)",
address = "United States",

}

Download

TY - GEN

T1 - An experiment of dual-LTE MPTCP with In-Car Voice Assistant

AU - Vu, Vu Anh

AU - Akselrod, Mark

N1 - Funding Information: Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - 227198829 / GRK1931 SocialCars.

PY - 2021/4

Y1 - 2021/4

N2 - The use of voice assistants in vehicles has been increasing drastically in recent years. Most of the current in-car assistants send voice commands to their cloud server to recognize the speech, process the requests, and return responses. Given that the Vehicle-to-Infrastructure connection quality is sufficient, the response times should be negligible, so that users and their assistants can keep a seamless conversation. The vast majority of current in-car systems are using LTE to connect to the Internet, even though not every LTE provider offers good coverage, especially on highways. In this paper, we investigate the use of multiple LTE providers to enhance connection availability and robustness. To combine multiple LTE interfaces into a single connection, we use MPTCP - a TCP extension that enables multi-path transmission. This work evaluates the voice response latency of MPTCP with two well-known schedulers (Lowest-RTT-first and Redundant) and compares them to single LTE configurations in three setups: emulated network, stationary, and in-car mobile measurements.

AB - The use of voice assistants in vehicles has been increasing drastically in recent years. Most of the current in-car assistants send voice commands to their cloud server to recognize the speech, process the requests, and return responses. Given that the Vehicle-to-Infrastructure connection quality is sufficient, the response times should be negligible, so that users and their assistants can keep a seamless conversation. The vast majority of current in-car systems are using LTE to connect to the Internet, even though not every LTE provider offers good coverage, especially on highways. In this paper, we investigate the use of multiple LTE providers to enhance connection availability and robustness. To combine multiple LTE interfaces into a single connection, we use MPTCP - a TCP extension that enables multi-path transmission. This work evaluates the voice response latency of MPTCP with two well-known schedulers (Lowest-RTT-first and Redundant) and compares them to single LTE configurations in three setups: emulated network, stationary, and in-car mobile measurements.

KW - interactive application

KW - MPTCP

KW - multi-path scheduling

KW - transport protocol

KW - V2I

KW - voice assistant

UR - http://www.scopus.com/inward/record.url?scp=85112420663&partnerID=8YFLogxK

U2 - 10.1109/VTC2021-Spring51267.2021.9448971

DO - 10.1109/VTC2021-Spring51267.2021.9448971

M3 - Conference contribution

AN - SCOPUS:85112420663

SN - 978-1-7281-8965-9

T3 - IEEE Vehicular Technology Conference

BT - 2021 IEEE 93rd Vehicular Technology Conference (VTC 2021-Spring - Proceedings)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 93rd IEEE Vehicular Technology Conference (VTC 2021-Spring)

Y2 - 25 April 2021 through 28 April 2021

ER -