Welcome to the homepage of David Rybach

I was a research assistant at the Human Language Technology and Pattern Recognition Group of RWTH Aachen University. Currently, I work at Google, New York.

The research topics of the group are: Pattern Recognition, Human Language Technology, and Image Processing.

My personal research interests include automatic speech recognition with focus on efficient search methods and weighted finite-state transducers. I maintained RASR, the RWTH Aachen University Open Source Speech Recognition System.

2013

• D. Rybach, H. Ney, and R. Schlüter. Lexical Prefix Tree and WFST: A Comparison of Two Dynamic Search Concepts for LVCSR. Audio, Speech, and Language Processing, IEEE Transactions on, volume 21, number 6, pages 1295 -1307, June 2013.
  ©
• M. Kozielski, D. Rybach, S. Hahn, R. Schlüter, and H. Ney. Open Vocabulary Handwriting Recognition using Combined Word-level and Character-level Language Models. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, May 2013.
  

2012

• M. A. Basha Shaik, D. Rybach, S. Hahn, R. Schlüter, and H. Ney. Hierarchical Hybrid Language models for Open Vocabulary Continuous Speech Recognition using WFST. In Workshop on Statistical and Perceptual Audition (SAPA), pages 46-51, Portland, OR, USA, September 2012.
  
• P. Dreuw, D. Rybach, G. Heigold, and H. Ney. RWTH OCR: A Large Vocabulary Optical Character Recognition System for Arabic Scripts. In Volker Märgner, and Haikal El Abed: Guide to OCR for Arabic Scripts Chp. Part II: Recognition, pages 215-254, Springer, London, UK, July 2012. ISBN 978-1-4471-4071-9.
  ©
• D. Rybach, R. Schlüter, and H. Ney. Silence is Golden: Modeling Non-speech Events in WFST-based Dynamic Network Decoders. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 4205-4208, Kyoto, Japan, March 2012.
  
• D. Nolden, D. Rybach, R. Schlüter, and H. Ney. Joining Advantages of Word-conditioned and Token-passing Decoding. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 4425-4428, Kyoto, Japan, March 2012.
  
• B. Hoffmeister, G. Heigold, D. Rybach, R. Schlüter, and H. Ney. WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding . Audio, Speech, and Language Processing, IEEE Transactions on, volume 20, number 2, pages 551-564 , February 2012.
  ©

2011

• D. Rybach, S. Hahn, P. Lehnen, D. Nolden, M. Sundermeyer, Z. Tüske, S. Wiesler, R. Schlüter, and H. Ney. RASR - The RWTH Aachen University Open Source Speech Recognition Toolkit. In IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), Hawaii, USA, December 2011.
  
• S. Hahn, and D. Rybach. Building an Open Vocabulary ASR System using Open Source Software. Interspeech, Florence, Italy, August 2011. Tutorial M3.
  
• D. Rybach, R. Schlüter, and H. Ney. A Comparative Analysis of Dynamic Network Decoding. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 5184-5187, Prague, Czech Republic, May 2011.
  

2010

• D. Rybach, and M. Riley. Direct Construction of Compact Context-Dependency Transducers From Data. In Interspeech, pages 218-221, Makuhari, Japan, September 2010. (corrected Figure 2). Best Paper Award..
  
• N. Parihar, R. Schlüter, D. Rybach, and E. A. Hansen. Parallel Lexical-tree Based LVCSR on Multi-core Processors. In Interspeech, pages 1485-1488, Makuhari, Japan, September 2010.
  

2009

• D. Rybach, C. Gollan, G. Heigold, B. Hoffmeister, J. Lööf, R. Schlüter, and H. Ney. The RWTH Aachen University Open Source Speech Recognition System. In Interspeech, pages 2111-2114, Brighton, UK, September 2009.
  
• N. Parihar, R. Schlüter, D. Rybach, and E. A. Hansen. Parallel Fast Likelihood Computation for LVCSR using Mixture Decomposition. In Interspeech, pages 3047-3050, Brighton, UK, September 2009.
  
• G. Heigold, D. Rybach, R. Schlüter, and H. Ney. Investigations on Convex Optimization Using Log-Linear HMMs for Digit String Recognition. In Interspeech, pages 216-219, Brighton, UK, September 2009.
  
• A. El-Desoky Mousa, C. Gollan, D. Rybach, R. Schlüter, and H. Ney. Investigating the Use of Morphological Decomposition and Diacritization for Improving Arabic LVCSR. In Interspeech, pages 2679-2682, Brighton, UK, September 2009.
  
• H. Schulz, J. A. R. Fonollosa, and D. Rybach. Transcription of Catalan Broadcast Conversation. In International Conference on Text, Speech and Dialogue (TSD), pages 154-161, Pilsen, Czech Republic, September 2009.
  
• P. Dreuw, D. Rybach, C. Gollan, and H. Ney. Writer Adaptive Training and Writing Variant Model Refinement for Offline Arabic Handwriting Recognition. In International Conference on Document Analysis and Recognition (ICDAR), pages 21-25, Barcelona, Spain, July 2009.
  ©
• D. Rybach, C. Gollan, R. Schlüter, and H. Ney. Audio Segmentation for Speech Recognition using Segment Features. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 4197-4200, Taipei, Taiwan, April 2009.
  

2008

• R. Schlüter, C. Gollan, S. Hahn, G. Heigold, B. Hoffmeister, J. Lööf, C. Plahl, D. Rybach, and H. Ney. Development of Large Vocabulary ASR Systems for Mandarin and Arabic. In ITG-Fachtagung Sprachkommunikation (Sprachkommunikation), Aachen, Germany, October 2008.
  
• D. Vergyri, A. Mandal, W. Wang, A. Stolcke, J. Zheng, M. Graciarena, D. Rybach, C. Gollan, R. Schlüter, K. Kirchhoff, A. Faria, and N. Morgan. Development of the SRI/Nightingale Arabic ASR system. In Interspeech, pages 1437-1440, Brisbane, Australia, September 2008.
  
• P. Dreuw, D. Stein, T. Deselaers, D. Rybach, M. Zahedi, J. Bungeroth, and H. Ney. Spoken Language Processing Techniques for Sign Language Recognition and Translation. Technology and Dissability, volume 20, number 2, pages 121-133, Amsterdam, The Netherlands, June 2008.
  

2007

• D. Rybach, S. Hahn, C. Gollan, R. Schlüter, and H. Ney. Advances in Arabic Broadcast News Transcription at RWTH. In IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 449-454, Kyoto, Japan, December 2007.
  
• P. Dreuw, D. Rybach, T. Deselaers, M. Zahedi, and H. Ney. Speech Recognition Techniques for a Sign Language Recognition System. In Interspeech, pages 2513-2516, Antwerp, Belgium, August 2007. ISCA best student paper award Interspeech 2007.
  
• J. Lööf, C. Gollan, S. Hahn, G. Heigold, B. Hoffmeister, C. Plahl, D. Rybach, R. Schlüter, and H. Ney. The RWTH 2007 TC-STAR Evaluation System for European English and Spanish. In Interspeech, pages 2145-2148, Antwerp, Belgium, August 2007.
  

2006

• M. Zahedi, P. Dreuw, D. Rybach, T. Deselaers, and H. Ney. Using Geometric Features to Improve Continuous Appearance-based Sign Language Recognition. In British Machine Vision Conference (BMVC), volume 3, pages 1019-1028, Edinburgh, UK, September 2006.
  
• D. Rybach. Appearance-Based Features for Automatic Continuous Sign Language Recognition. Master Thesis, Aachen, Germany, June 2006.
  
• M. Zahedi, P. Dreuw, D. Rybach, T. Deselaers, J. Bungeroth, and H. Ney. Continuous Sign Language Recognition - Approaches from Speech Recognition and Available Data Resources. In LREC Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios, pages 21-24, Genoa, Italy, May 2006.
  
• P. Dreuw, T. Deselaers, D. Rybach, D. Keysers, and H. Ney. Tracking Using Dynamic Programming for Appearance-Based Sign Language Recognition. In IEEE International Conference on Automatic Face and Gesture Recognition (FG), IEEE, pages 293-298, Southampton, UK, April 2006.
  ©

2005

• T. Deselaers, D. Rybach, P. Dreuw, D. Keysers, and H. Ney. Face-based Image Retrieval -­ One Step Toward Object-based Image Retrieval. In MUSCLE / ImageCLEF Workshop on Image and Video Retrieval Evaluation, pages 25-32, Vienna, Austria, September 2005.
  
• D. Rybach, D. Keysers, and H. Ney. Erweiterung eines holistischen statistischen Bilderkenners zur Verwendung von mehreren Merkmalen. In Informatiktage der Gesellschaft für Informatik, pages inpress, St. Augustin, Germany, April 2005.