José María Lahoz-Bengoechea


2024

pdf bib
Automated Extraction of Prosodic Structure from Unannotated Sign Language Video
Antonio F. G. Sevilla | José María Lahoz-Bengoechea | Alberto Diaz
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

As in oral phonology, prosody is an important carrier of linguistic information in sign languages. One of the most prominent ways this reveals itself is in the time structure of signs: their rhythm and intensity of articulation. To be able to empirically see these effects, the velocity of the hands can be computed throughout the execution of a sign. In this article, we propose a method for extracting this information from unlabeled videos of sign language, exploiting CoTracker, a recent advancement in computer vision which can track every point in a video without the need of any calibration or fine-tuning. The dominant hand is identified via clustering of the computed point velocities, and its dynamic profile plotted to make apparent the prosodic structure of signing. We apply our method to different datasets and sign languages, and perform a preliminary visual exploration of results. This exploration supports the usefulness of our methodology for linguistic analysis, though issues to be tackled remain, such as bi-manual signs and a formal and numerical evaluation of accuracy. Nonetheless, the absence of any preprocessing requirements may make it useful for other researchers and datasets.

2022

pdf bib
Quevedo: Annotation and Processing of Graphical Languages
Antonio F. G. Sevilla | Alberto Díaz Esteban | José María Lahoz-Bengoechea
Proceedings of the Thirteenth Language Resources and Evaluation Conference

In this article, we present Quevedo, a software tool we have developed for the task of automatic processing of graphical languages. These are languages which use images to convey meaning, relying not only on the shape of symbols but also on their spatial arrangement in the page, and relative to each other. When presented in image form, these languages require specialized computational processing which is not the same as usually done either for natural language processing or for artificial vision. Quevedo enables this specialized processing, focusing on a data-based approach. As a command line application and library, it provides features for the collection and management of image datasets, and their machine learning recognition using neural networks and recognizer pipelines. This processing requires careful annotation of the source data, for which Quevedo offers an extensive and visual web-based annotation interface. In this article, we also briefly present a case study centered on the task of SignWriting recognition, the original motivation for writing the software. Quevedo is written in Python, and distributed freely under the Open Software License version 3.0.

2020

pdf bib
Tools for the Use of SignWriting as a Language Resource
Antonio F. G. Sevilla | Alberto Díaz Esteban | José María Lahoz-Bengoechea
Proceedings of the LREC2020 9th Workshop on the Representation and Processing of Sign Languages: Sign Language Resources in the Service of the Language Community, Technological Challenges and Application Perspectives

Representation of linguistic data is an issue of utmost importance when developing language resources, but the lack of a standard written form in sign languages presents a challenge. Different notation systems exist, but only SignWriting seems to have some use in the native signer community. It is, however, a difficult system to use computationally, not based on a linear sequence of characters. We present the project “VisSE”, which aims to develop tools for the effective use of SignWriting in the computer. The first of these is an application which uses computer vision to interpret SignWriting, understanding the meaning of new or existing transcriptions, or even hand-written images. Two additional tools will be able to consume the result of this recognizer: first, a textual description of the features of the transcription will make it understandable for non-signers. Second, a three-dimensional avatar will be able to reproduce the configurations and movements contained within the transcription, making it understandable for signers even if not familiar with SignWriting. Additionally, the project will result in a corpus of annotated SignWriting data which will also be of use to the computational linguistics community.