Syntactic Reanalysis in Language Models for Speech Recognition

Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob), pages 215--220, doi:10.1109/DEVLRN.2017.8329810 - Sep 2017.
Associated documents : twiefel_ICDL_EpiRob_2017_self_archive.pdf [283Ko]   http://dx.doi.org/10.1109/DEVLRN.2017.8329810
State-of-the-art speech recognition systems steadily increase their performance using different variants of deep neural networks and postprocess the results by employing N-gram statistical models trained on a large amount of data coming from the general-purpose domain. While achieving an excellent performance regarding Word Error Rate (17.343% on our HumanRobot Interaction data set), state-of-the-art systems generate hypotheses that are grammatically incorrect in 57.316% of the cases. Moreover, if employed in a restricted domain (e.g. HumanRobot Interaction), around 50% of the hypotheses contain out-ofdomain words. The latter are confused with similarly pronounced in-domain words and cannot be interpreted by a domain-specific inference system. The state-of-the-art speech recognition systems lack a mechanism that addresses the syntactic correctness of hypotheses. We propose a system that can detect and repair grammatically incorrect or infrequent sentence forms. It is inspired by a computational neuroscience model that we developed previously. The current system is still a proof-of-concept version of a future neurobiologically more plausible neural network model. Hence, the resulting system postprocesses sentence hypotheses of state-ofthe-art speech recognition systems, producing in-domain words in 100% of the cases, syntactically and grammatically correct hypotheses in 90.319% of the cases. Moreover, it reduces the Word Error Rate to 11.038%.

 

@InProceedings{THW17,
  author       = "Twiefel, Johannes and Hinaut, Xavier and Wermter, Stefan",
  title        = "Syntactic Reanalysis in Language Models for Speech Recognition",
  booktitle    = "Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob)",
  pages        = "215--220",
  month        = "Sep",
  year         = "2017",
  publisher    = "IEEE",
  doi          = "10.1109/DEVLRN.2017.8329810",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2017/THW17/twiefel_ICDL_EpiRob_2017_self_archive.pdf"
}

» Johannes Twiefel
» Xavier Hinaut
» Stefan Wermter