Sebastian Tschöpel

I am a researcher and software engineer in NetMedia's speech group at Fraunhofer IAIS. I received my master's degree in information and media technologies from the Brandenburg University of Technology Cottbus, where I focused my studies on digital speech signal processing and software engineering at the chair of Prof. Fellbaum.

Current focus areas

  • Language modeling
  • Information retrieval on speech recognition transcripts
  • Software engineering

Publications

  • Tschöpel, S.; Schneider, D.; (2010): A lightweight keyword and tag-cloud retrieval algorithm for automatic speech recognition transcripts. 11th Annual Conference of the International Speech Communication Association (INTERSPEECH)
  • Wittenburg, P.; Auer, E.; Sloetjes, H.; Schreer, O.; Masneri, S.; Schneider, D.; Tschöpel, S.; (2010): Automatic Annotation of Media Field Recordings. International workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities (LaTeCH-10)
  • Masneri, S.; Schreer, O.; Schneider, D.; Tschöpel, S.; Bardeli, R.; et. al. (2010): Towards semi-automatic annotation of video and audio corpora. 7th international conference on Language Resources and Evaluation (LREC)
  • Wittenburg, P.; Schreer, O.; Schneider, D.; Tschöpel, S.; et.al (2010): ELAN as Flexible Annotation Framework for Sound and Image Processing Detectors. 7th international conference on Language Resources and Evaluation (LREC)

Vita

since Aug. 2009
Research fellow NetMedia, Fraunhofer IAIS
Apr. 2009 - Jul. 2009
Student fellow NetMedia, Fraunhofer IAIS
Oct. 2006 - Apr. 2009
Master of Science, Information- and Media Technology (BTU Cottbus)
Student assistant at chair of Media Technologies (BTU Cottbus)
Student assistant at chair of Communication Engineering (BTU Cottbus)
Student assistant at multimedia center (BTU Cottbus)
Oct. 2003 - Oct. 2006
Bachelor of Science, Information- and Media Technology (University of Technology, Cottbus)
Mar. 1983
Born in Cottbus, Germany

Latest blog entries

Our research paper "A lightweight keyword and tag-cloud retrieval algorithm for automatic speech recognition transcripts" has been accepted for the INTERSPEECH 2010 11th Annual Conference of the International Speech Communication Association (ISCA). INTERSPEECH is one of the world's largest and most comprehensive conference on issues surrounding the science and technology of spoken language processing both in humans and in machines.

Categories

Our AVATecH community paper "Automatic Annotation of Media Field Recordings" was accepted for the LATeCH-2010 workshop on language technology for cultural heritage, social sciences, and humanities that will be held in conjunction with the 19th European Conference on Artificial Intelligence (ECAI 2010).

Categories

Ever spend hours on debugging and unknoting java code?

Categories