@inproceedings{RiedhammerGroppBockletetal.2013, author = {Riedhammer, Korbinian and Gropp, Martin and Bocklet, Tobias and H{\"o}nig, Florian and N{\"o}th, Elmar and Steidl, Stefan}, title = {LMELectures: A Multimedia Corpus of Academic Spoken English}, series = {First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), Marseille, France, August 2013, ISCA Archive.}, booktitle = {First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013), Marseille, France, August 2013, ISCA Archive.}, pages = {102 -- 107}, year = {2013}, abstract = {This paper describes the acquisition, transcription and annotation of a multi-media corpus of academic spoken English, the LMELectures. It consists of two lecture se-ries that were read in the summer term 2009 at the com-puter science department of the University of Erlangen-Nuremberg, covering topics in pattern analysis, machine learning and interventional medical image processing. In total, about 40 hours of high-definition audio and video of a single speaker was acquired in a constant recording en-vironment. In addition to the recordings, the presentation slides are available in machine readable (PDF) format. The manual annotations include a suggested segmenta-tion into speech turns and a complete manual transcrip-tion that was done using BLITZSCRIBE2, a new tool for the rapid transcription. For one lecture series, the lecturer assigned key words to each recordings; one recording of that series was further annotated with a list of ranked key phrases by five human annotators each. The corpus is available for non-commercial purpose upon request.}, language = {en} }