Dynamic–static unsupervised sequentiality, statistical subunits and lexicon for sign language recognition

作者:

Highlights:

• A phonetic modeling approach for unsupervised sequentiality of dynamic-static SUs.

• Model based sign segmentation and subunit modeling with HMMs.

• Construction of a sign-to-subunits data-driven lexicon.

• Comparison of different signers' pronunciations and unseen signer pronunciation compensation.

• Evaluation on data from three corpora, two sign languages and unseen signers.

摘要

•A phonetic modeling approach for unsupervised sequentiality of dynamic-static SUs.•Model based sign segmentation and subunit modeling with HMMs.•Construction of a sign-to-subunits data-driven lexicon.•Comparison of different signers' pronunciations and unseen signer pronunciation compensation.•Evaluation on data from three corpora, two sign languages and unseen signers.

论文关键词:Automatic sign language recognition,Data-driven subunits,Sub-sign phonetic modeling,Unsupervised,Segmentation,HMM

论文评审过程:Received 22 May 2013, Revised 27 March 2014, Accepted 30 April 2014, Available online 9 May 2014.

论文官网地址:https://doi.org/10.1016/j.imavis.2014.04.012