Advances in phonetics-based sub-unit modeling for transcription alignment and sign language recognition

Pitsikalis, Vassilis; Theodorakis, Stavros; Vogler, Christian; Maragos, Petros

doi:10.1109/cvprw.2011.5981681

Cited by 44 publications

(31 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The trees are 2.7% more accurate when n = 1, becoming 7.9% better when n = 10. Work has been done on a subset of 961 signs from the same dataset by Pitsikalis et al [9]. They use a more complex set of features based on linguistics and combine them using HMMs.…”

Section: Results Ii: (982 Sign Database)mentioning

confidence: 99%

See 1 more Smart Citation

Sign Language Recognition using Sequential Pattern Trees

Ong

Cooper

Pugeault

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

This paper presents a novel, discriminative, multi-class classifier based on Sequential Pattern Trees. It is efficient to learn, compared to other Sequential Pattern methods, and scalable for use with large classifier banks. For these reasons it is well suited to Sign Language Recognition. Using deterministic robust features based on hand trajectories, sign level classifiers are built from sub-units. Results are presented both on a large lexicon single signer data set and a multi-signer Kinect TM data set. In both cases it is shown to out perform the non-discriminative Markov model approach and be equivalent to previous, more costly, Sequential Pattern (SP) techniques.

show abstract

Section: Results Ii: (982 Sign Database)mentioning

confidence: 99%

“…They present results for a dictionary containing 1113 signs [12]. More recently, Pitsikalis et al [9] proposed a method which uses linguistic labelling to split signs into sub-units. From this they learn signer specific models, which are then combined via HMMs to create a classifier over 961 signs.…”

Section: Introductionmentioning

confidence: 99%

Sign Language Recognition using Sequential Pattern Trees

Ong

Cooper

Pugeault

et al. 2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Recently, an extended sequential Posture-Detention-Transition-Steady Shift model has been published [9] which fixes some of its predecessor's shortcomings on movements with attached location information. Pitsikalis et al [13] employ this system to improve sign language recognition using subunits generated on a forced alignment of previously annotated hamnosys transcriptions. They work with data of a single signer containing five iterations of 961 isolated signs.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, they do not allow to add new signs to the system without retraining it, similar to how it is done in speech recognition. In addition, there is an increasing body of research reporting superior results using linguistically motivated subunits [10], [1], [13]. This work combines both worlds, as it leverages from an existing linguistic source.…”

Section: Introductionmentioning

confidence: 99%

May the force be with you: Force-aligned signwriting for automatic subunit annotation of corpora

Koller

Ney

Bowden

2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

View full text Add to dashboard Cite

Abstract-We propose a method to generate linguistically meaningful subunits in a fully automated fashion for sign language corpora. The ability to automate the process of subunit annotation has profound effects on the data available for training sign language recognition systems. The approach is based on the idea that subunits are shared among different signs. With sufficient data and knowledge of possible signing variants, accurate automatic subunit sequences are produced, matching the specific characteristics of given sign language data.Specifically we demonstrate how an iterative forced alignment algorithm can be used to transfer the knowledge of a useredited open sign language dictionary to the task of annotating a challenging, large vocabulary, multi-signer corpus recorded from public TV. Existing approaches focus on labour intensive manual subunit annotations or on data-driven approaches. Our method yields an average precision and recall of 15% under the maximum achievable accuracy with little user intervention beyond providing a simple word gloss.

show abstract

“…One prevalent family of methods for SLR are Hidden Markov Models (HMMs). Pitsikalis et al [9] proposed a method which uses linguistic labelling to split signs into sub-units. From this they learn signer specific models, which are then combined via HMMs to create a classifier.…”

Section: Introductionmentioning

confidence: 99%