@inproceedings{dreuw:10001:sign-lang:lrec,
  author    = {Dreuw, Philippe and Forster, Jens and Gweth, Yannick and Stein, Daniel and Ney, Hermann and Mart{\'i}nez Ruiz, Gregorio and Verges Llahi, Jaume and Crasborn, Onno and Ormel, Ellen and Du, Wei and Hoyoux, Thomas and Piater, Justus and Moya Lazaro, Jos{\'e} Miguel and Wheatley, Mark},
  title     = {{SignSpeak} - Understanding, Recognition, and Translation of Sign Languages},
  pages     = {65--72},
  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/10001.html},
  abstract  = {The SignSpeak project will be the first step to approach sign language recognition and translation at a scientific level already reached in similar research fields such as automatic speech recognition or statistical machine translation of spoken languages. Deaf communities revolve around sign languages as they are their natural means of communication. Although deaf, hard of hearing and hearing signers can communicate without problems amongst themselves, there is a serious challenge for the deaf community in trying to integrate into educational, social and work environments. The overall goal of SignSpeak is to develop a new vision-based technology for recognizing and translating continuous sign language to text. New knowledge about the nature of sign language structure from the perspective of machine recognition of continuous sign language will allow a subsequent breakthrough in the development of a new vision-based technology for continuous sign language recognition and translation. Existing and new publicly available corpora will be used to evaluate the research progress throughout the whole project.}
}

@inproceedings{pitsikalis:10049:sign-lang:lrec,
  author    = {Pitsikalis, Vassilis and Theodorakis, Stavros and Maragos, Petros},
  title     = {Data-Driven Sub-Units, Modeling Structure of Multiple Cues for Continuous Sign Language Recognition},
  pages     = {196--203},
  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/10049.html},
  abstract  = {We investigate the automatic phonetic modeling of sign language based on phonetic sub-units, which are data driven and without any prior phonetic information. Visual processing is based on a probabilistic skin color model and a framewise geodesic active contour segmentation; occlusions are handled by a forward-backward prediction component leading finally to simple and effective region-based visual features. For sign-language modeling we propose a modeling structure for data-driven sub-unit construction. This utilizes the cue that is considered crucial to segment the signal into parts; at the same time we also classify the segments by implicitly assigning labels of Dynamic or Static type. This segmentation and classification step disentangles Dynamic from Static parts and allows us to employ for each type of segment the appropriate cue, modeling and clustering approach. The constructed Dynamic segments are exploited at the model level via hidden Markov models (HMMs). The Static segments are exploited via k-means clustering. Each Dynamic or Static part, exploits the appropriate cue related to the movement. We propose that the movement cues are normalized in order to be translation and scale invariant. We apply the proposed modeling for further combination of the movement trajectory individual cues. The proposed approaches are evaluated in recognition experiments conducted on the continuous sign language corpus of Boston University (BU-400) showing promising preliminary results.}
}

@inproceedings{dreuw-etal-2010-signspeak:lrec,
  author    = {Dreuw, Philippe and Ney, Hermann and Mart{\'i}nez Ruiz, Gregorio and Crasborn, Onno and Piater, Justus and Moya Lazaro, Jos{\'e} Miguel and Wheatley, Mark},
  title     = {The {SignSpeak} Project - Bridging the Gap Between Signers and Speakers},
  pages     = {476--481},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel},
  booktitle = {7th International Conference on Language Resources and Evaluation ({LREC} 2010)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Valletta, Malta},
  day       = {17--23},
  month     = may,
  year      = {2010},
  isbn      = {978-2-9517408-6-0},
  language  = {english},
  url       = {https://aclanthology.org/L10-1238},
  abstract  = {The SignSpeak project will be the first step to approach sign language recognition and translation at a scientific level already reached in similar research fields such as automatic speech recognition or statistical machine translation of spoken languages. Deaf communities revolve around sign languages as they are their natural means of communication. Although deaf, hard of hearing and hearing signers can communicate without problems amongst themselves, there is a serious challenge for the deaf community in trying to integrate into educational, social and work environments. The overall goal of SignSpeak is to develop a new vision-based technology for recognizing and translating continuous sign language to text. New knowledge about the nature of sign language structure from the perspective of machine recognition of continuous sign language will allow a subsequent breakthrough in the development of a new vision-based technology for continuous sign language recognition and translation. Existing and new publicly available corpora will be used to evaluate the research progress throughout the whole project.}
}

@inproceedings{dreuw-etal-2008-benchmark:lrec,
  author    = {Dreuw, Philippe and Neidle, Carol and Athitsos, Vassilis and Sclaroff, Stan and Ney, Hermann},
  title     = {Benchmark Databases for Video-Based Automatic Sign Language Recognition},
  pages     = {1115--1120},
  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/L08-1469},
  abstract  = {A new, linguistically annotated, video database for automatic sign language recognition is presented. The new RWTH-BOSTON-400 corpus, which consists of 843 sentences, several speakers and separate subsets for training, development, and testing is described in detail. For evaluation and benchmarking of automatic sign language recognition, large corpora are needed. Recent research has focused mainly on isolated sign language recognition methods using video sequences that have been recorded under lab conditions using special hardware like data gloves. Such databases have often consisted generally of only one speaker and thus have been speaker-dependent, and have had only small vocabularies. A new database access interface, which was designed and created to provide fast access to the database statistics and content, makes it possible to easily browse and retrieve particular subsets of the video database. Preliminary baseline results on the new corpora are presented. In contradistinction to other research in this area, all databases presented in this paper will be publicly available.}
}