@inproceedings{jedlicka:22039:sign-lang:lrec, author = {Jedli{\v c}ka, Pavel and Kr{\v n}oul, Zden{\v e}k and {\v Z}elezn{\'y}, Milo{\v s} and M{\"u}ller, Lud{\v e}k}, title = {{MC-TRISLAN}: A Large {3D} Motion Capture Sign Language Data-set}, pages = {88--93}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna and Schulder, Marc}, booktitle = {Proceedings of the {LREC2022} 10th Workshop on the Representation and Processing of Sign Languages: Multilingual Sign Language Resources}, maintitle = {13th International Conference on Language Resources and Evaluation ({LREC} 2022)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {25}, month = jun, year = {2022}, isbn = {979-10-95546-86-3}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/22039.html}, abstract = {The new 3D motion capture data corpus expands the portfolio of existing language resources by a corpus of 18~hours of Czech sign language. This helps to alleviate the current problem, which is a critical lack of high quality data necessary for research and subsequent deployment of machine learning techniques in this area. We currently provide the largest collection of annotated sign language recordings acquired by state-of-the-art 3D human body recording technology for the successful future deployment in communication technologies, especially machine translation and sign language synthesis.} } @inproceedings{jedlicka:20027:sign-lang:lrec, author = {Jedli{\v c}ka, Pavel and Kr{\v n}oul, Zden{\v e}k and Kanis, Jakub and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Sign Language Motion Capture Dataset for Data-driven Synthesis}, pages = {101--106}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {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}, maintitle = {12th International Conference on Language Resources and Evaluation ({LREC} 2020)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marseille, France}, day = {16}, month = may, year = {2020}, isbn = {979-10-95546-54-2}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/20027.html}, abstract = {This paper presents a new 3D motion capture dataset of Czech Sign Language (CSE). Its main purpose is to provide the data for further analysis and data-based automatic synthesis of CSE utterances. The content of the data in the given limited domain of weather forecasts was carefully selected by the CSE linguists to provide the necessary utterances needed to produce any new weather forecast. The dataset was recorded using the state-of-the-art motion capture (MoCap) technology to provide the most precise trajectories of the motion. In general, MoCap is a device capable of accurate recording of motion directly in 3D space. The data contains trajectories of body, arms, hands and face markers recorded at once to provide consistent data without the need for the time alignment.} } @inproceedings{kimmelman-etal-2018-ipsl:lrec, author = {Kimmelman, Vadim and Klezovich, Anna and Moroz, George}, title = {{IPSL}: A Database of Iconicity Patterns in Sign Languages. Creation and Use}, pages = {4230--4234}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1667} } @inproceedings{yu-etal-2018-sign:lrec, author = {Yu, Shi and Geraci, Carlo and Abner, Natasha}, title = {Sign Languages and the Online World Online Dictionaries {\&} Lexicostatistics}, pages = {4235--4240}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Cieri, Christopher and Declerck, Thierry and Goggi, Sara and Hasida, Koiti and Isahara, Hitoshi and Maegaard, Bente and Mariani, Joseph and Mazo, H{\'e}l{\`e}ne and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios and Tokunaga, Takenobu}, booktitle = {11th International Conference on Language Resources and Evaluation ({LREC} 2018)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Miyazaki, Japan}, day = {7--12}, month = may, year = {2018}, isbn = {979-10-95546-00-9}, language = {english}, url = {https://aclanthology.org/L18-1668} } @inproceedings{jedlicka:16022:sign-lang:lrec, author = {Jedli{\v c}ka, Pavel and Kr{\v n}oul, Zden{\v e}k and {\v Z}elezn{\'y}, Milo{\v s}}, title = {Methods for Recognizing Interesting Events within Sign Language Motion Capture Data}, pages = {101--104}, editor = {Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna}, booktitle = {Proceedings of the {LREC2016} 7th Workshop on the Representation and Processing of Sign Languages: Corpus Mining}, maintitle = {10th International Conference on Language Resources and Evaluation ({LREC} 2016)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Portoro{\v z}, Slovenia}, day = {28}, month = may, year = {2016}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/16022.html}, abstract = {Rising popularity of motion capture in movie-production makes this technology more robust and more accessible. Utilization of this technology for sign language capturing and analysis is evident. The article deals with the usability of the motion capture in creating sign language corpora. A large amount of the data acquired by the motion capture has to be processed to provide usable data for wide range of research areas: e.g. sign language recognition, translation, synthesis, linguistics, etc. The aim of this article is to explore possible methods to detect interesting events in data using machine learning techniques. The result is a method for detection of the beginning and the end of the sign, hand location, finger and palm orientation, whether the sign is one or two handed, and symmetry in the two-handed signs.} } @inproceedings{campr:10043:sign-lang:lrec, author = {Campr, Pavel and Hr{\'u}z, Marek and Langer, Ji{\v r}{\'i} and Kanis, Jakub and {\v Z}elezn{\'y}, Milo{\v s} and M{\"u}ller, Lud{\v e}k}, title = {Towards {Czech} on-line sign language dictionary -- technological overview and data collection}, pages = {41--44}, editor = {Dreuw, Philippe and Efthimiou, Eleni and Hanke, Thomas and Johnston, Trevor and Mart{\'i}nez Ruiz, Gregorio and Schembri, Adam}, booktitle = {Proceedings of the {LREC2010} 4th Workshop on the Representation and Processing of Sign Languages: Corpora and Sign Language Technologies}, maintitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Valletta, Malta}, day = {22--23}, month = may, year = {2010}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/10043.html}, abstract = {In this article we present the current state of our work on an on-line sign language dictionary. The aim is to create both an explanatory and a translation dictionary. It is primarily targeted (but not limited) to the Czech and Czech sign language. At first we describe technological aspects of the dictionary and then our data collection practices. The dictionary is an on-line application build with respect to the linguistic needs. We use written text to represent spoken languages and several representations are supported for sign languages: videos, images, HamNoSys, SignWriting and interactive 3D avatar. To decrease time required for data collection and publishing in the dictionary we use computer vision methods for video analysis to detect sign boundaries and analyze the manual component of performed sign for automatic categorization. The content will be created by linguists using both new and already existing data. Then, the dictionary will be opened to the public with possibility to add, modify and comment data. We expect that this possibility of on-line elicitation will increase the number of informants, cover more regions and makes the elicitation cheaper and the evaluation easier. Furthermore we prepare a mobile interface of the dictionary. The mobile interface will use different format of web pages and different video compression methods optimized for slower Internet connection. We also prepare an offline version of the dictionary which can be automatically generated from the online content and downloaded for offline usage.} } @inproceedings{kanis:08012:sign-lang:lrec, author = {Kanis, Jakub and Kr{\v n}oul, Zden{\v e}k}, title = {Interactive {HamNoSys} Notation Editor for Signed Speech Annotation}, pages = {88--93}, editor = {Crasborn, Onno and Efthimiou, Eleni and Hanke, Thomas and Thoutenhoofd, Ernst D. and Zwitserlood, Inge}, booktitle = {Proceedings of the {LREC2008} 3rd Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora}, maintitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {1}, month = jun, year = {2008}, language = {english}, url = {https://www.sign-lang.uni-hamburg.de/lrec/pub/08012.html}, abstract = {The goal of sign language synthesis is to create an avatar which uses sign languge as main communication form. In order to emulate human behaviour during signing the avatar has to express manual components (hand position, hand shape) and non-manual components (face expression, lip articulation) of the performed signs. The task of sign language synthesis is implemented in several steps. Since the sign language has different grammar than the spoken language, the source sentence has to be translated into corresponding sequence of isolated signs. Those signs are synthesized in sequence and create output sentence in sign language. Non-manual components are synthesized by already developed Czech talking head which is able to articulate words and sentences in Czech language. Face expressions can be manually set. The synthesis process of manual movements is based on HamNoSys 3.0 notation. This notation is used for deterministic and suitable processing of the sign speech. The methodology of the notation allows precise and also extensible expression of the sign description. \par Firstly, our synthesis system automatically carries out the syntactic analysis of symbolic string (in HamNoSys notation) and generates a tree structure. The tree structure is suitable for conversion of the symbols to tra jectories with application parse rules. The parsing rules were manually formed to cover all HamNoSys notation variants. There are 39 rule actions forming complete animation tra jectories. For this purpose 138 HamNoSys symbols are currently adopted. The processing of the tree is carried out by several tree walks whilst the size of the tree is reduced. The final animation tra jectories in the root node are transformed by an inverse kinematics technique to control the joints of avatar animation model. The analysis of HamNoSys symbols allows us to animate hands and the upper half-body. Thus a single sign is encoded by corresponding sequence of HamNoSys symbols. \par We have developed an interactive tool which purpose is to extend our database of signs. The main application window contains list of symbols which can be clicked and added into the sequence. This sequence can be immediately converted into the movement of the avatar which is shown in the second window. This allows fast production of symbol sequences for new signs and easy modification of existing signs since the changes are directly visible. In addition it allows people who have no high experince with HamNoSys to learn it faster. At present our database contains about 300 signs which are encoded as sequeces of HamNoSys symbols. This first database is targeted to the information system for train connections. Further expansion of the database will add new areas where the avatar can be used.} } @inproceedings{campr-etal-2008-collection:lrec, author = {Campr, Pavel and Hr{\'u}z, Marek and Trojanov{\'a}, Jana}, title = {Collection and Preprocessing of {C}zech {S}ign {L}anguage Corpus for Sign Language Recognition}, pages = {3175--3178}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Tapias, Daniel}, booktitle = {6th International Conference on Language Resources and Evaluation ({LREC} 2008)}, publisher = {{European Language Resources Association (ELRA)}}, address = {Marrakech, Morocco}, day = {26}, month = may, year = {2008}, isbn = {978-2-9517408-4-6}, language = {english}, url = {https://aclanthology.org/L08-1471}, abstract = {This paper discusses the design, recording and preprocessing of a Czech sign language corpus. The corpus is intended for training and testing of sign language recognition (SLR) systems. The UWB-07-SLR-P corpus contains video data of 4 signers recorded from 3 different perspectives. Two of the perspectives contain whole body and provide 3D motion data, the third one is focused on signer’s face and provide data for face expression and lip feature extraction. Each signer performed 378 signs with 5 repetitions. The corpus consists of several types of signs: numbers (35 signs), one and two-handed finger alphabet (64), town names (35) and other signs (244). Each sign is stored in a separate AVI file. In total the corpus consists of 21853 video files in total length of 11.1 hours. Additionally each sign is preprocessed and basic features such as 3D hand and head trajectories are available. The corpus is mainly focused on feature extraction and isolated SLR rather than continuous SLR experiments.} }