@inproceedings{22218,
  author       = {{Krauter, Stefan and Böcker, Joachim and Freitag, Christine and Hehenkamp, Burkhard and Hilleringmann, Ulrich and Temmen, Katrin and Klaus, Tobias and Rohrer, Nicolaus and Lehmann, Sven}},
  booktitle    = {{Tagungsband des 36. PV-Symposiums, 18.-26 Mai 2021}},
  isbn         = {{978-3-948176-14-3}},
  keywords     = {{Art-D, Afrika, Resilienz, Resilience, Grid stability, robustness, microgrids}},
  location     = {{Staffelstein / online}},
  pages        = {{305--309}},
  publisher    = {{Conexio}},
  title        = {{{Projekt Art-D Grids: Nachhaltige und stabile Microgrids in Afrika - eine Plattform für Forschung und Lehre für die Entwicklung}}},
  year         = {{2021}},
}

@article{11867,
  abstract     = {{New waves of consumer-centric applications, such as voice search and voice interaction with mobile devices and home entertainment systems, increasingly require automatic speech recognition (ASR) to be robust to the full range of real-world noise and other acoustic distorting conditions. Despite its practical importance, however, the inherent links between and distinctions among the myriad of methods for noise-robust ASR have yet to be carefully studied in order to advance the field further. To this end, it is critical to establish a solid, consistent, and common mathematical foundation for noise-robust ASR, which is lacking at present. This article is intended to fill this gap and to provide a thorough overview of modern noise-robust techniques for ASR developed over the past 30 years. We emphasize methods that are proven to be successful and that are likely to sustain or expand their future applicability. We distill key insights from our comprehensive overview in this field and take a fresh look at a few old problems, which nevertheless are still highly relevant today. Specifically, we have analyzed and categorized a wide range of noise-robust techniques using five different criteria: 1) feature-domain vs. model-domain processing, 2) the use of prior knowledge about the acoustic environment distortion, 3) the use of explicit environment-distortion models, 4) deterministic vs. uncertainty processing, and 5) the use of acoustic models trained jointly with the same feature enhancement or model adaptation process used in the testing stage. With this taxonomy-oriented review, we equip the reader with the insight to choose among techniques and with the awareness of the performance-complexity tradeoffs. The pros and cons of using different noise-robust ASR techniques in practical application scenarios are provided as a guide to interested practitioners. The current challenges and future research directions in this field is also carefully analyzed.}},
  author       = {{Li, Jinyu and Deng, Li and Gong, Yifan and Haeb-Umbach, Reinhold}},
  journal      = {{IEEE Transactions on Audio, Speech and Language Processing}},
  keywords     = {{Speech recognition, compensation, distortion modeling, joint model training, noise, robustness, uncertainty processing}},
  number       = {{4}},
  pages        = {{745--777}},
  title        = {{{An Overview of Noise-Robust Automatic Speech Recognition}}},
  doi          = {{10.1109/TASLP.2014.2304637}},
  volume       = {{22}},
  year         = {{2014}},
}

@article{11825,
  abstract     = {{In this paper, we propose an enhanced error concealment strategy at the server side of a distributed speech recognition (DSR) system, which is fully compatible with the existing DSR standard. It is based on a Bayesian approach, where the a posteriori probability density of the error-free feature vector is computed, given all received feature vectors which are possibly corrupted by transmission errors. Rather than computing a point estimate, such as the MMSE estimate, and plugging it into the Bayesian decision rule, we employ uncertainty decoding, which results in an integration over the uncertainty in the feature domain. In a typical scenario the communication between the thin client, often a mobile device, and the recognition server spreads across heterogeneous networks. Both bit errors on circuit-switched links and lost data packets on IP connections are mitigated by our approach in a unified manner. The experiments reveal improved robustness both for small- and large-vocabulary recognition tasks.}},
  author       = {{Ion, Valentin and Haeb-Umbach, Reinhold}},
  journal      = {{Speech Communication}},
  keywords     = {{Channel error robustness, Distributed speech recognition, Soft features, Uncertainty decoding}},
  number       = {{11}},
  pages        = {{1435--1446}},
  title        = {{{Uncertainty decoding for distributed speech recognition over error-prone networks}}},
  doi          = {{10.1016/j.specom.2006.03.007}},
  volume       = {{48}},
  year         = {{2006}},
}