About me
I'm a researcher at the Fraunhofer IAIS speech group, and I'm responsible for the research strategy of the group.
My current research focus is on speech search in large digital archives, which should finally enable you to search in the spoken content of a 10,000 hour video archive.
I received my diploma degree in computer science from the RWTH Aachen University, where I focused my studies on statistical pattern recognition and natural language processing at the chair of Prof. Ney. After finishing my diploma thesis about "Rapid Signer Adaptation for Isolated Sign Language Recognition" I joined the Fraunhofer IAIS speech group in 2006.
From 2007-2010 I was the project manager at IAIS for the EU-funded project VITALAS, focusing on large scale multimedia search. Since 2009, I am also responsible for the AVATECH project, where our group collaborates with the Max-Planck Institute for Psycholinguistics in order to support linguistic analysis with automatic tools.
Some other activities:
I'm a member of IEEE and GI.
Related Publications
Contextual Verification for Open Vocabulary Spoken Term Detection. Daniel Schneider, Timo Mertens, Martha Larson, Joachim Köhler. Proc. INTERSPEECH, Makuhari, 2010.
A lightweight keyword and tag-cloud retrieval algorithm for automatic speech recognition transcripts.
Sebastian Tschöpel, Daniel Schneider. Proc.
INTERSPEECH, Makuhari, 2010.
Constrained Subword Units for Speaker Recognition. Doris Baum, Daniel Schneider, Timo Mertens, Joachim Köhler. Proc. Odyssey, 2010.
Spoken Term Detection on German Speech Data. Daniel Schneider, Joachim Köhler. Proc. ITG Symposium on Speech Communications, 2010.
DiSCo - A German Evaluation Corpus for Challenging Problems in the Broadcast Domain. Doris Baum, Daniel Schneider et. al. Proc. LREC, 2010.
Towards semi-automatic annotation of video and audio corpora. Stefano Masneri, Oliver Schreer, Daniel Schneider, Sebastian Tschöpel, Rolf Bardeli et. al.
Proc. LREC, 2010.
ELAN as flexible annotation framework for sound and image processing detectors. Peter Wittenburg, Oliver Schreer, Daniel Schneider et. al. Proc. LREC, 2010.
Automatic Annotation of Media Field Recordings.
Peter Wittenburg, Eric Auer, Han Slotjes, Oliver Schreer, Stefano
Masneri, Daniel Schneider, Sebastian Tschöpel. Proc. LaTeCH, 2010.
Efficient subword lattice retrieval for German spoken
term detection. Timo Mertens, Daniel Schneider. Proc. IEEE ICASSP, Taipeh, 2009, S. 4885-4888
Lexicon adaptation for subword speech recognition. Timo Mertens, Daniel Schneider, Arild
Brandrud Naess, Torbjørn Svendsen. Proc. IEEE ASRU, Merano, 2009, S. 562-567
Merging search spaces for subword spoken term
detection. Timo Mertens, Daniel Schneider, Joachim Köhler. Proc. INTERSPEECH, Brighton, 2009.
Audio clips content comparison using latent semantic
indexing. Konstantin Biatov, Joachim Köhler, Daniel Schneider. Proc. IEEE ICSC, Berkeley, 2009, S. 509-512
Information and knowlege management. Gerhard Paaß, Daniel Schneider, Stefan Wrobel. In: Technology
guide: principles, applications, trends. Springer, 2009,
S. 276-281
DiSCo - a speaker and speech recognition evaluation
corpus for challenging problems in the broadcast domain. Doris Baum, Barbara Samlowski, Thomas Winkler, Rolf Bardeli, Daniel Schneider. Proc. GSCL Symposium, Duisburg, 2009
Towards Large Scale Vocabulary Independent Spoken
Term Detection. Daniel Schneider, Jochen Schon, Stefan Eickeler. Proc. ACM SIGIR SSCS Workshop, Singapore, 2008, S. 34-41.
Robust Audio Indexing and Keyword Retrieval Optimized for the Rescue Opeeration Domain. Daniel Schneider, Thomas Winkler, Jobst Löffler, Jochen Schon. Proc. Mobile Response, 2007
Rapid Signer Adaptation for Isolated Sign Language Recognition. Ulrich v. Agris, Daniel Schneider, Jörg Zieren, Farl-Friedrich Kraiss. In Proc. IEEE CVPR Workshop on Sign Language Recognition, 2006
