@inproceedings{koller:16036:sign-lang:lrec,
  author    = {Koller, Oscar and Ney, Hermann and Bowden, Richard},
  title     = {Automatic Alignment of {HamNoSys} Subunits for Continuous Sign Language Recognition},
  pages     = {121--128},
  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/16036.html},
  abstract  = {This work presents our recent advances in the field of automatic processing of sign language corpora targeting continuous sign language recognition. We demonstrate how generic annotations at the articulator level, such as HamNoSys, can be exploited to learn subunit classifiers. Specifically, we explore cross-language-subunits of the hand orientation modality, which are trained on isolated signs of publicly available lexicon data sets for Swiss German and Danish sign language and are applied to continuous sign language recognition of the challenging RWTH-PHOENIX-Weather corpus featuring German sign language. We observe a significant reduction in word error rate using this method.}
}

@inproceedings{koller:14031:sign-lang:lrec,
  author    = {Koller, Oscar and Ney, Hermann and Bowden, Richard},
  title     = {Weakly supervised automatic transcription of mouthings for gloss-based sign language corpora},
  pages     = {89--94},
  editor    = {Crasborn, Onno and Efthimiou, Eleni and Fotinea, Stavroula-Evita and Hanke, Thomas and Hochgesang, Julie A. and Kristoffersen, Jette and Mesch, Johanna},
  booktitle = {Proceedings of the {LREC2014} 6th Workshop on the Representation and Processing of Sign Languages: Beyond the Manual Channel},
  maintitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Reykjavik, Iceland},
  day       = {31},
  month     = may,
  year      = {2014},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/14031.html},
  abstract  = {In this work we propose a method to automatically annotate mouthings in sign language corpora, requiring no more than a simple gloss annotation and a source of weak supervision, such as automatic speech transcripts. For a long time, research on automatic recognition of sign language has focused on the manual components. However, a full understanding of sign language is not possible without exploring its remaining parameters. Mouthings provide important information to disambiguate homophones with respect to the manuals. Nevertheless most corpora for pattern recognition purposes are lacking any mouthing annotations. To our knowledge no previous work exists that automatically annotates mouthings in the context of sign language. Our method produces a frame error rate of 39{\%} for a single signer.}
}

@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{forster:10038:sign-lang:lrec,
  author    = {Forster, Jens and Stein, Daniel and Ormel, Ellen and Crasborn, Onno and Ney, Hermann},
  title     = {Best Practice for Sign Language Data Collections Regarding the Needs of Data-Driven Recognition and Translation},
  pages     = {92--97},
  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/10038.html},
  abstract  = {We propose best practices for gloss annotation of sign languages taking into account the needs of data-driven approaches to recognition and translation of natural languages. Furthermore, we provide reference numbers for several technical aspects for the creation of new sign language data collections. Most available sign language data collections are of limited use to data-driven approaches, because they focus on rare sign language phenomena, or lack machine readable annotation schemes. Using a natural language processing point of view, we briefly discuss several sign language data collection, propose best practices for gloss annotation stemming from experience gained using two large scale sign language data collections, and derive reference numbers for several technical aspects from standard benchmark data collections for speech recognition and translation.}
}

@inproceedings{stein:10014:sign-lang:lrec,
  author    = {Stein, Daniel and Forster, Jens and Zelle, Uwe and Dreuw, Philippe and Ney, Hermann},
  title     = {{RWTH-Phoenix}: Analysis of the {German} {Sign} {Language} Weather Forecast Corpus},
  pages     = {225--230},
  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/10014.html},
  abstract  = {In this work, the recent additions to the RWTH-Phoenix corpus, a data collection of interpreted news announcement, are analysed. The corpus features videos, gloss annotation of German Sign Language and transcriptions of spoken German. The annotation procedure is reported, and the corpus statistics are discussed. We present automatic machine translation results for both directions, and discuss syntactically motivated enhancements.}
}

@inproceedings{dreuw:08038:sign-lang:lrec,
  author    = {Dreuw, Philippe and Ney, Hermann},
  title     = {Towards Automatic Sign Language Annotation for the {ELAN} Tool},
  pages     = {50--53},
  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/08038.html},
  abstract  = {A new interface to the ELAN annotation software that can handle automatically generated annotations by a sign language recognition and translation framework is described. For evaluation and benchmarking of automatic sign language recognition, large corpora with rich annotation are needed. Such databases have generally only small vocabularies and are created for linguistic purposes, because the annotation process of sign language videos is time consuming and requires expert knowledge of bilingual speakers (signers). The proposed framework provides easy access to the output of an automatic sign language recognition and translation framework. Furthermore, new annotations and metadata information can be added and imported into the ELAN annotation software. Preliminary results show that the performance of a statistical machine translation improves using automatically generated annotations.
\par
Automatic sign language recognition is a problem that is being solved by many research institutes in the world. Up to now there is a deficiency of corpora with good properties such as high resolution and frame rate, several views of the scene, detailed annotation etc. In this paper we take a closer look at the annotation of available data.}
}

@inproceedings{zahedi:06005:sign-lang:lrec,
  author    = {Zahedi, Morteza and Dreuw, Philippe and Rybach, David and Deselaers, Thomas and Bungeroth, Jan and Ney, Hermann},
  title     = {Continuous Sign Language Recognition -- Approaches from Speech Recognition and Available Data Resources},
  pages     = {21--24},
  editor    = {Vettori, Chiara},
  booktitle = {Proceedings of the {LREC2006} 2nd Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios},
  maintitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Genoa, Italy},
  day       = {28},
  month     = may,
  year      = {2006},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/06005.html},
  abstract  = {In this paper we describe our current work on automatic continuous sign language recognition. We present an automatic sign language recognition system that is based on a large vocabulary speech recognition system and adopts many of the approaches that are conven- tionally applied in the recognition of spoken language. Furthermore, we present a set of freely available databases that can be used for training, testing and performance evaluation of sign language recognition systems. First results on one of the databases are given, we show that the approaches from spoken language recognition are suitable, and we give directions for further research.}
}

@inproceedings{bungeroth:04021:sign-lang:lrec,
  author    = {Bungeroth, Jan and Ney, Hermann},
  title     = {Statistical Sign Language Translation},
  pages     = {105--108},
  editor    = {Streiter, Oliver and Vettori, Chiara},
  booktitle = {Proceedings of the {LREC2004} Workshop on the Representation and Processing of Sign Languages: From {SignWriting} to Image Processing. Information techniques and their implications for teaching, documentation and communication},
  maintitle = {4th International Conference on Language Resources and Evaluation ({LREC} 2004)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Lisbon, Portugal},
  day       = {30},
  month     = may,
  year      = {2004},
  language  = {english},
  url       = {https://www.sign-lang.uni-hamburg.de/lrec/pub/04021.html},
  abstract  = {In the field of machine translation, significant progress has been made by using statistical methods. In this paper we suggest a statistical machine translation system for Sign Language and written language, especially for the language pair German Sign Language (DGS) and German. After introducing the system's architecture, statistical machine translation in general and notation systems for Sign Language, the corpus processing is scetched. Finally, preliminary translation results are presented.}
}

@inproceedings{forster-etal-2014-extensions:lrec,
  author    = {Forster, Jens and Schmidt, Christoph and Koller, Oscar and Bellgardt, Martin and Ney, Hermann},
  title     = {Extensions of the Sign Language Recognition and Translation Corpus {RWTH}-{PHOENIX}-{Weather}},
  pages     = {1911--1916},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Loftsson, Hrafn and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios,},
  booktitle = {9th International Conference on Language Resources and Evaluation ({LREC} 2014)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Reykjavik, Iceland},
  day       = {26--31},
  month     = may,
  year      = {2014},
  isbn      = {978-2-9517408-8-4},
  language  = {english},
  url       = {https://aclanthology.org/L14-1472},
  doi       = {10.63317/27pdd6xpkah6},
  abstract  = {This paper introduces the RWTH-PHOENIX-Weather 2014, a video-based, large vocabulary, German sign language corpus which has been extended over the last two years, tripling the size of the original corpus. The corpus contains weather forecasts simultaneously interpreted into sign language which were recorded from German public TV and manually annotated using glosses on the sentence level and semi-automatically transcribed spoken German extracted from the videos using the open-source speech recognition system RASR. Spatial annotations of the signers' hands as well as shape and orientation annotations of the dominant hand have been added for more than 40k respectively 10k video frames creating one of the largest corpora allowing for quantitative evaluation of object tracking algorithms. Further, over 2k signs have been annotated using the SignWriting annotation system, focusing on the shape, orientation, movement as well as spatial contacts of both hands. Finally, extended recognition and translation setups are defined, and baseline results are presented.}
}

@inproceedings{forster-etal-2012-rwth:lrec,
  author    = {Forster, Jens and Schmidt, Christoph and Hoyoux, Thomas and Koller, Oscar and Zelle, Uwe and Piater, Justus and Ney, Hermann},
  title     = {{RWTH}-{PHOENIX}-{Weather}: A Large Vocabulary Sign Language Recognition and Translation Corpus},
  pages     = {3785--3789},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Declerck, Thierry and Do{\u g}an, Mehmet U{\u g}ur and Maegaard, Bente and Mariani, Joseph and Moreno, Asuncion and Odijk, Jan and Piperidis, Stelios},
  booktitle = {8th International Conference on Language Resources and Evaluation ({LREC} 2012)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Istanbul, Turkey},
  day       = {21--27},
  month     = may,
  year      = {2012},
  isbn      = {978-2-9517408-7-7},
  language  = {english},
  url       = {https://aclanthology.org/L12-1503},
  doi       = {10.63317/4vmmiu4jeew5},
  abstract  = {This paper introduces the RWTH-PHOENIX-Weather corpus, a video-based, large vocabulary corpus of German Sign Language suitable for statistical sign language recognition and translation. In contrastto most available sign language data collections, the RWTH-PHOENIX-Weather corpus has not been recorded for linguistic research but for the use in statistical pattern recognition. The corpus contains weather forecasts recorded from German public TV which are manually annotated using glosses distinguishing sign variants, and time boundaries have been marked on the sentence and the gloss level. Further, the spoken German weather forecast has been transcribed in a semi-automatic fashion using a state-of-the-art automatic speech recognition system. Moreover, an additional translation of the glosses into spoken German has been created to capture allowable translation variability. In addition to the corpus, experimental baseline results for hand and head tracking, statistical sign language recognition and translation are presented.}
}

@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},
  doi       = {10.63317/4omuh5dhw6za},
  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},
  doi       = {10.63317/4wzouow58zat},
  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.}
}

@inproceedings{bungeroth-etal-2008-atis:lrec,
  author    = {Bungeroth, Jan and Stein, Daniel and Dreuw, Philippe and Ney, Hermann and Morrissey, Sara and Way, Andy and van Zijl, Lynette},
  title     = {The {ATIS} Sign Language Corpus},
  pages     = {2943--2946},
  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/L08-1470},
  doi       = {10.63317/52zjy2i8c79h},
  abstract  = {Systems that automatically process sign language rely on appropriate data. We therefore present the ATIS sign language corpus that is based on the domain of air travel information. It is available for five languages, English, German, Irish sign language, German sign language and South African sign language. The corpus can be used for different tasks like automatic statistical translation and automatic sign language recognition and it allows the specific modeling of spatial references in signing space.}
}

@inproceedings{bungeroth-etal-2006-german:lrec,
  author    = {Bungeroth, Jan and Stein, Daniel and Dreuw, Philippe and Zahedi, Morteza and Ney, Hermann},
  title     = {A {G}erman {S}ign {L}anguage Corpus of the Domain Weather Report},
  pages     = {2000--2003},
  editor    = {Calzolari, Nicoletta and Choukri, Khalid and Gangemi, Aldo and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Tapias, Daniel},
  booktitle = {5th International Conference on Language Resources and Evaluation ({LREC} 2006)},
  publisher = {{European Language Resources Association (ELRA)}},
  address   = {Genoa, Italy},
  day       = {22--28},
  month     = may,
  year      = {2006},
  isbn      = {978-2-9517408-2-2},
  language  = {english},
  url       = {https://aclanthology.org/L06-1418},
  doi       = {10.63317/5hcqquw2odw9},
  abstract  = {All systems for automatic sign language translation and recognition, in particular statistical systems, rely on adequately sized corpora. For this purpose, we created the Phoenix corpus that is based on German television weather reports translated into German Sign Language. It comes with a rich annotation of the video data, a bilingual text-based sentence corpus and a monolingual German corpus. All systems for automatic sign language translation and recognition, in particular statistical systems, rely on adequately sized corpora. For this purpose, we created the Phoenix corpus that is based on German television weather reports translated into German Sign Language. It comes with a rich annotation of the video data, a bilingual text-based sentence corpus and a monolingual German corpus.}
}