Name
Title | ||
|---|---|---|
May the force be with you: Force-aligned signwriting for automatic subunit annotation of corpora |
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 user-edited 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. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/FG.2013.6553777 | Automatic Face and Gesture Recognition |
Keywords | Field | DocType |
gesture recognition,iterative methods,automatic subunit annotation,automatic subunit sequences,data-driven approaches,force-aligned sign writing,iterative forced alignment algorithm,knowledge transfer,labour intensive manual subunit annotations,multisigner corpus,process automation,public TV,sign language corpora,sign language data,sign language recognition systems,signing variants,sufficient data,user intervention,user-edited open sign language dictionary,vocabulary | Annotation,Iterative method,Computer science,Precision and recall,Gesture recognition,Speech recognition,Sign language,Natural language processing,Artificial intelligence,SignWriting,Hidden Markov model,Vocabulary | Conference |
ISSN | ISBN | Citations |
2326-5396 | 978-1-4673-5544-5 | 9 |
PageRank | References | Authors |
0.57 | 12 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Oscar Koller | 1 | 128 | 9.02 |
| Hermann Ney | 2 | 14178 | 1506.93 |
| Richard Bowden | 3 | 1840 | 118.50 |