Challenge based visual speech recognition using deep learning

Philip McShane; Darryl Stewart

doi:10.23919/ICITST.2017.8356433

Challenge based visual speech recognition using deep learning

Philip McShane
, Darryl Stewart

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

2 Citations (Scopus)

Abstract

We present a novel approach to liveness verification based on visual speech recognition within a challenge-based framework which has the potential to be used on mobile devices to prevent replay or spoof attacks during Face-based liveness verification. The system uses model visual speech recognition and determines liveness based on the Levenshtein Distance between a randomly generated challenge phrase and the hypothesis utterances from the visual speech recognizer. A Deep learning-based approach to visual speech recognition is used to improve upon the state of the art for the use of visual speech recognition for liveness verification.

Original language	English
Title of host publication	12th International Conference for Internet Technology and Secured Transactions (ICITST 2017): Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	405-410
Number of pages	6
ISBN (Electronic)	9781908320933
DOIs	https://doi.org/10.23919/ICITST.2017.8356433
Publication status	Published - 10 May 2018
Event	12th International Conference for Internet Technology and Secured Transactions, ICITST 2017 - Cambridge, United Kingdom Duration: 11 Dec 2017 → 14 Dec 2017

Conference

Conference	12th International Conference for Internet Technology and Secured Transactions, ICITST 2017
Country/Territory	United Kingdom
City	Cambridge
Period	11/12/2017 → 14/12/2017

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Hardware and Architecture
Safety, Risk, Reliability and Quality

Access to Document

10.23919/ICITST.2017.8356433Licence: Unspecified

Cite this

@inproceedings{42d49311476941599ff8c3b12efee10e,

title = "Challenge based visual speech recognition using deep learning",

abstract = "We present a novel approach to liveness verification based on visual speech recognition within a challenge-based framework which has the potential to be used on mobile devices to prevent replay or spoof attacks during Face-based liveness verification. The system uses model visual speech recognition and determines liveness based on the Levenshtein Distance between a randomly generated challenge phrase and the hypothesis utterances from the visual speech recognizer. A Deep learning-based approach to visual speech recognition is used to improve upon the state of the art for the use of visual speech recognition for liveness verification.",

author = "Philip McShane and Darryl Stewart",

year = "2018",

month = may,

day = "10",

doi = "10.23919/ICITST.2017.8356433",

language = "English",

pages = "405--410",

booktitle = "12th International Conference for Internet Technology and Secured Transactions (ICITST 2017): Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "12th International Conference for Internet Technology and Secured Transactions, ICITST 2017 ; Conference date: 11-12-2017 Through 14-12-2017",

}

McShane, P & Stewart, D 2018, Challenge based visual speech recognition using deep learning. in 12th International Conference for Internet Technology and Secured Transactions (ICITST 2017): Proceedings. Institute of Electrical and Electronics Engineers Inc., pp. 405-410, 12th International Conference for Internet Technology and Secured Transactions, ICITST 2017, Cambridge, United Kingdom, 11/12/2017. https://doi.org/10.23919/ICITST.2017.8356433

TY - GEN

T1 - Challenge based visual speech recognition using deep learning

AU - McShane, Philip

AU - Stewart, Darryl

PY - 2018/5/10

Y1 - 2018/5/10

N2 - We present a novel approach to liveness verification based on visual speech recognition within a challenge-based framework which has the potential to be used on mobile devices to prevent replay or spoof attacks during Face-based liveness verification. The system uses model visual speech recognition and determines liveness based on the Levenshtein Distance between a randomly generated challenge phrase and the hypothesis utterances from the visual speech recognizer. A Deep learning-based approach to visual speech recognition is used to improve upon the state of the art for the use of visual speech recognition for liveness verification.

AB - We present a novel approach to liveness verification based on visual speech recognition within a challenge-based framework which has the potential to be used on mobile devices to prevent replay or spoof attacks during Face-based liveness verification. The system uses model visual speech recognition and determines liveness based on the Levenshtein Distance between a randomly generated challenge phrase and the hypothesis utterances from the visual speech recognizer. A Deep learning-based approach to visual speech recognition is used to improve upon the state of the art for the use of visual speech recognition for liveness verification.

UR - https://www.scopus.com/pages/publications/85048034713

U2 - 10.23919/ICITST.2017.8356433

DO - 10.23919/ICITST.2017.8356433

M3 - Conference contribution

AN - SCOPUS:85048034713

SP - 405

EP - 410

BT - 12th International Conference for Internet Technology and Secured Transactions (ICITST 2017): Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th International Conference for Internet Technology and Secured Transactions, ICITST 2017

Y2 - 11 December 2017 through 14 December 2017

ER -

Challenge based visual speech recognition using deep learning

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Visual speech recognition in sparse data domains

Cite this

Challenge based visual speech recognition using deep learning

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Student theses

Visual speech recognition in sparse data domains

Cite this