David Rybach

David Rybach is currently a Software Engineer at Google. His research focuses on decoding methods for automatic speech recognition and related topics. He received his PhD from RWTH Aachen University in 2014.

Google Publications

Previous Publications

  •   

    Direct construction of compact context-dependency transducers from data

    David Rybach, Michael Riley, Chris Alberti

    Computer Speech & Language, vol. 28 (2014), pp. 177-191

  •   

    Lexical Prefix Tree and WFST: A Comparison of Two Dynamic Search Concepts for LVCSR

    David Rybach, Hermann Ney, Ralf Schlüter

    IEEE Transactions on Audio, Speech, and Language Processing, vol. 21 (2013), pp. 1295-307

  •   

    Open Vocabulary Handwriting Recognition Using Combined Word-Level and Character-Level Language Models

    Michal Kozielski, David Rybach, Stefan Hahn, Ralf Schlüter, Hermann Ney

    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2013), pp. 8257-8261

  •  

    RWTH OCR: A Large Vocabulary Optical Character Recognition System for Arabic Scripts

    Philippe Dreuw, David Rybach, Georg Heigold, Hermann Ney

    Guide to OCR for Arabic Scripts, Springer (2012), pp. 215-254

  •   

    Silence is Golden: Modeling Non-speech Events in WFST-based Dynamic Network Decoders

    David Rybach, Ralf Schlüter, Hermann Ney

    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2012), pp. 4205-4208

  •   

    WFST Enabled Solutions to ASR Problems: Beyond HMM Decoding

    Björn Hoffmeister, Georg Heigold, David Rybach, Ralf Schlüter, Hermann Ney

    IEEE Transactions on Audio, Speech, and Language Processing, vol. 20 (2012), pp. 551-564

  •   

    A Comparative Analysis of Dynamic Network Decoding

    David Rybach, Ralf Schlüter, Hermann Ney

    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2011), pp. 5184-5187

  •   

    Audio Segmentation for Speech Recognition using Segment Features

    David Rybach, Christian Gollan, Ralf Schlüter, Hermann Ney

    IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2009), pp. 4197-4200

  •   

    Investigations on Convex Optimization Using Log-Linear HMMs for Digit String Recognition

    Georg Heigold, David Rybach, Ralf Schlüter, Hermann Ney

    Interspeech (2009), pp. 216-219

  •   

    The RWTH Aachen University Open Source Speech Recognition System

    David Rybach, Christian Gollan, Georg Heigold, Björn Hoffmeister, Jonas Lööf, Ralf Schlüter, Hermann Ney

    Interspeech (2009), pp. 2111-2114

  •   

    Writer Adaptive Training and Writing Variant Model Refinement for Offline Arabic Handwriting Recognition

    Philippe Dreuw, David Rybach, Christian Gollan, Hermann Ney

    International Conference on Document Analysis and Recognition (ICDAR) (2009), pp. 21-25

  •  

    Spoken Language Processing Techniques for Sign Language Recognition and Translation.

    Philippe Dreuw, Daniel Stein, Thomas Deselaers, David Rybach, Morteza Zahedi, Jan Bungeroth, Hermann Ney

    Technology and Dissability, vol. 20 (2008), pp. 121-133

  •   

    Advances in Arabic Broadcast News Transcription at RWTH

    David Rybach, Stefan Hahn, Christian Gollan, Ralf Schluter, Hermann Ney

    IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (2007), pp. 449-454

  •   

    Speech Recognition Techniques for a Sign Language Recognition System

    Philippe Dreuw, David Rybach, Thomas Deselaers, Morteza Zahedi, Hermann Ney

    Interspeech (2007), pp. 2513-2516