HMM-based Approaches to Model Multichannel Information in Sign Language Inspired from Articulatory Features-based Speech Processing

Sandrine Tornay; Marzieh Razavi; Necati Cihan Camgöz; Richard Bowden; Mathew Magimai-Doss

doi:10.1109/ICASSP.2019.8683167

Back

HMM-based Approaches to Model Multichannel Information in Sign Language Inspired from Articulatory Features-based Speech Processing

Conference presentation

Open access

HMM-based Approaches to Model Multichannel Information in Sign Language Inspired from Articulatory Features-based Speech Processing

Sandrine Tornay, Marzieh Razavi, Necati Cihan Camgöz, Richard Bowden and Mathew Magimai-Doss

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.2817-2821

Institute of Electrical and Electronics Engineers (IEEE)

2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019) (Brighton, UK, 12/05/2019 - 17/05/2019)

12/05/2019

DOI: https://doi.org/10.1109/ICASSP.2019.8683167

Abstract

Sign language; Subunits; Articulatory Features; Hidden Markov Model

Sign language conveys information through multiple channels, such as hand shape, hand movement, and mouthing. Modeling this multichannel information is a highly challenging problem. In this paper, we elucidate the link between spoken language and sign language in terms of production phenomenon and perception phenomenon. Through this link we show that hidden Markov model-based approaches developed to model "articulatory" features for spoken language processing can be exploited to model the multichannel information inherent in sign language for sign language processing.

Files and links (3)

pdf

HMM-based Approaches to Model Multichannel Information in Sign Language215.84 kBDownload View

Text Open Access

url

https://doi.org/10.1109/ICASSP.2019.8683167View

Published (Version of record)

url

https://2019.ieeeicassp.org/View

Organisation

Metrics

181 File views/ downloads

42 Record Views

Details

Title: HMM-based Approaches to Model Multichannel Information in Sign Language Inspired from Articulatory Features-based Speech Processing
Creators: Sandrine Tornay
Marzieh Razavi
Necati Cihan Camgöz
Richard Bowden
Mathew Magimai-Doss
Publication Details: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.2817-2821
Conference: 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019) (Brighton, UK, 12/05/2019 - 17/05/2019)
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date published: 12/05/2019
Date submitted: 07/05/2019
Identifiers: 99511903602346
Copyright: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Academic Unit: School of Computer Science and Electronic Engineering
Resource Type: Conference presentation

HMM-based Approaches to Model Multichannel Information in Sign Language Inspired from Articulatory Features-based Speech Processing

Abstract

Files and links (3)

Metrics

Details

Usage Policy