Accurate and Accessible Motion-Capture Glove Calibration for Sign Language Data Collection

2010 ◽  
Vol 3 (1) ◽  
pp. 1-32 ◽  
Author(s):  
Matt Huenerfauth ◽  
Pengfei Lu
Keyword(s):  
Data Collection ◽  
Sign Language ◽  
Motion Capture ◽  
Language Data

Current and future methodologies for quantitative analysis of information transfer in sign language and gesture data

2017 ◽  
Vol 40 ◽  
Author(s):  
Evie Malaia
Keyword(s):  
Quantitative Analysis ◽  
Data Collection ◽  
Sign Language ◽  
Motion Capture ◽  
Information Transfer ◽  
State Of The Art ◽  
Video Data ◽  
Noninvasive Methods ◽  
Video Recordings ◽  
Biological Differentiation

AbstractState-of-the-art methods of analysis of video data now include motion capture and optical flow from video recordings. These techniques allow for biological differentiation between visual communication and noncommunicative motion, enabling further inquiry into neural bases of communication. The requirements for additional noninvasive methods of data collection and automatic analysis of natural gesture and sign language are discussed.

ASL Sea Battle: Gamifying Sign Language Data Collection

2021 ◽  
Author(s):  
Danielle Bragg ◽  
Naomi Caselli ◽  
John W. Gallagher ◽  
Miriam Goldberg ◽  
Courtney J. Oka ◽  
...  
Keyword(s):  
Data Collection ◽  
Sign Language ◽  
Language Data

The FATE Landscape of Sign Language AI Datasets

2021 ◽  
Vol 14 (2) ◽  
pp. 1-45
Author(s):  
Danielle Bragg ◽  
Naomi Caselli ◽  
Julie A. Hochgesang ◽  
Matt Huenerfauth ◽  
Leah Katz-Hernandez ◽  
...  
Keyword(s):  
Sign Language ◽  
New Technology ◽  
Individual Data ◽  
Community Members ◽  
Sign Languages ◽  
Language Data ◽  
History Of ◽  
Language Technologies ◽  
And Storage ◽  
Access Mechanisms

Sign language datasets are essential to developing many sign language technologies. In particular, datasets are required for training artificial intelligence (AI) and machine learning (ML) systems. Though the idea of using AI/ML for sign languages is not new, technology has now advanced to a point where developing such sign language technologies is becoming increasingly tractable. This critical juncture provides an opportunity to be thoughtful about an array of Fairness, Accountability, Transparency, and Ethics (FATE) considerations. Sign language datasets typically contain recordings of people signing, which is highly personal. The rights and responsibilities of the parties involved in data collection and storage are also complex and involve individual data contributors, data collectors or owners, and data users who may interact through a variety of exchange and access mechanisms. Deaf community members (and signers, more generally) are also central stakeholders in any end applications of sign language data. The centrality of sign language to deaf culture identity, coupled with a history of oppression, makes usage by technologists particularly sensitive. This piece presents many of these issues that characterize working with sign language AI datasets, based on the authors’ experiences living, working, and studying in this space.

Enabling Real-time Sign Language Translation on Mobile Platforms with On-board Depth Cameras

2021 ◽  
Vol 5 (2) ◽  
pp. 1-30
Author(s):  
HyeonJung Park ◽  
Youngki Lee ◽  
JeongGil Ko
Keyword(s):  
Real Time ◽  
Sign Language ◽  
Data Augmentation ◽  
Language Translation ◽  
Mobile Platforms ◽  
Depth Cameras ◽  
Language Data ◽  
In The Wild ◽  
Environmental Robustness ◽  
Cloud Servers

In this work we present SUGO, a depth video-based system for translating sign language to text using a smartphone's front camera. While exploiting depth-only videos offer benefits such as being less privacy-invasive compared to using RGB videos, it introduces new challenges which include dealing with low video resolutions and the sensors' sensitiveness towards user motion. We overcome these challenges by diversifying our sign language video dataset to be robust to various usage scenarios via data augmentation and design a set of schemes to emphasize human gestures from the input images for effective sign detection. The inference engine of SUGO is based on a 3-dimensional convolutional neural network (3DCNN) to classify a sequence of video frames as a pre-trained word. Furthermore, the overall operations are designed to be light-weight so that sign language translation takes place in real-time using only the resources available on a smartphone, with no help from cloud servers nor external sensing components. Specifically, to train and test SUGO, we collect sign language data from 20 individuals for 50 Korean Sign Language words, summing up to a dataset of ~5,000 sign gestures and collect additional in-the-wild data to evaluate the performance of SUGO in real-world usage scenarios with different lighting conditions and daily activities. Comprehensively, our extensive evaluations show that SUGO can properly classify sign words with an accuracy of up to 91% and also suggest that the system is suitable (in terms of resource usage, latency, and environmental robustness) to enable a fully mobile solution for sign language translation.

scholarly journals Kesalahan Berbahasa dalam Modul I Bahasa Indonesia PPG Dalam Jabatan Tahun 2020

2021 ◽  
Vol 9 (2) ◽  
pp. 193
Author(s):  
Rahmad Hidayat
Keyword(s):  
Data Analysis ◽  
Data Collection ◽  
Word Formation ◽  
Matching Method ◽  
Linguistic Rules ◽  
Language Data ◽  
Linguistic Categories ◽  
Word Writing ◽  
Writing Errors ◽  
Bahasa Indonesia

This research is here to explain several forms of errors in the material module of the Pendidikan Profesi Guru Dalam Jabatan Tahun 2020. Research on the analysis of language errors in the PPG module has never been carried out.  In data collection, used the Listening method with the Note Technique.  The data are recorded in such a way in tabulations.  In analyzing the data, the Intralingual Matching method was used with HBS and HBB techniques. HBS and HBB techniques are realized by comparing between language data and applicable rules.  Furthermore, deviant linguistic data are classified based on the types of violations against linguistic rules and theories.  The presentation of the results of data analysis in this study is based on the taxonomy of linguistic categories in language error analysis.  The results showed that in the module I PPG Dalam Jabatan Tahun 2020 there were spelling errors in the form of punctuation errors, capital letters errors, italicization errors, and word writing errors; morphological errors in the form of word formation errors and word non-conformity; syntactic errors in the form of misuse of conjunctor and ineffective sentences.

scholarly journals Deaf Ni-Vanuatu and their signs: A sociolinguistic study

2021 ◽  
Author(s):  
◽  
Jacqueline Iseli
Keyword(s):  
Data Collection ◽  
Sign Language ◽  
Deaf People ◽  
Deaf Community ◽  
Sign Languages ◽  
Individual Variations ◽  
Field Methodology ◽  
Degree Of Similarity ◽  
Similarity Of Signs

<p>This thesis provides the first documentation and description of the signs created and used by deaf individuals in Vanuatu. The specific aims of this research were as follows: to establish the sociolinguistic context experienced by deaf people in Vanuatu; to identify the repertoire and characteristics of signs used by the deaf participants; to compare features of participants’ individual signs with the characteristics of home signs and emerging sign languages; and to consider the degree of similarity and potential similarity of signs between participants and how this reflects individuals’ opportunities for contact with other deaf people and signing interlocutors. The limitations of this study are that field methodology for data collection was developed in situ as conditions allowed. The sociolinguistic context for deaf Ni-Vanuatu confirms that language isolation leads to marginalisation from community and society. The study established that these home sign lexicons were limited in quantity and conceptual range, and that shared background knowledge was essential for comprehension. Overall, 22 handshapes were documented, and the predominant handshapes unmarked. Most participants preferred handling strategy for depicting signs. Some evidence of noun-verb distinction was noted in the repertoire of some participants. However, across this range of formational characteristics, results showed significant individual variations. Furthermore, multiple barriers have precluded development of a shared sign language and any form of deaf community.</p>

scholarly journals From a Smoking Gun to Spent Fuel: Principled Subsampling Methods for Building Big Language Data Corpora from Monitor Corpora

Data ◽  
2019 ◽  
Vol 4 (2) ◽  
pp. 48 ◽  
Author(s):  
Jacqueline Tidwell
Keyword(s):  
Data Collection ◽  
Sampling Method ◽  
Evaluation Process ◽  
Spent Fuel ◽  
Social Scientists ◽  
Multiple Sampling ◽  
Language Data ◽  
Representative Model ◽  
Data Culture ◽  
Final Text

With the influence of Big Data culture on qualitative data collection, acquisition, and processing, it is becoming increasingly important that social scientists understand the complexity underlying data collection and the resulting models and analyses. Systematic approaches for creating computationally tractable models need to be employed in order to create representative, specialized reference corpora subsampled from Big Language Data sources. Even more importantly, any such method must be tested and vetted for its reproducibility and consistency in generating a representative model of a particular population in question. This article considers and tests one such method for Big Language Data downsampling of digitally accessible language data to determine both how to operationalize this form of corpus model creation, as well as testing whether the method is reproducible. Using the U.S. Nuclear Regulatory Commission’s public documentation database as a test source, the sampling method’s procedure was evaluated to assess variation in the rate of which documents were deemed fit for inclusion or exclusion from the corpus across four iterations. After performing multiple sampling iterations, the approach pioneered by the Tobacco Documents Corpus creators was deemed to be reproducible and valid using a two-proportion z-test at a 99% confidence interval at each stage of the evaluation process–leading to a final mean rejection ratio of 23.5875 and variance of 0.891 for the documents sampled and evaluated for inclusion into the final text-based model. The findings of this study indicate that such a principled sampling method is viable, thus necessitating the need for an approach for creating language-based models that account for extralinguistic factors and linguistic characteristics of documents.

Sign in / Sign up

Export Citation Format

Share Document