Publications: Hynek Hermansky

2017

Conference Proceedings

  1. Meyer, Bernd T., Sri Harish Mallidi, Hendrik Kayser, and Hynek Hermansky. “Predicting error rates for unknown data in automatic speech recognition.” In Acoustics, Speech and Signal Processing (ICASSP), 2017 IEEE International Conference on, pp. 5330-5334. IEEE, 2017.

Journal

  1. Wang, Xiaofei, Yonghong Yan, and Hynek Hermansky. “Stream Attention for far-field multi-microphone ASR.” arXiv preprint arXiv:1711.11141 (2017).

2016

Journal

  1. Mallidi, Sri Harish Reddy, and Hynek Hermansky. “A Framework for Practical Multistream ASR.” In INTERSPEECH, pp. 3474-3478. 2016.
  2. Spille, Constantin, Hendrik Kayser, Hynek Hermansky, and Bernd T. Meyer. “Assessing Speech Quality in Speech-Aware Hearing Aids Based on Phoneme Posteriorgrams.” In INTERSPEECH, pp. 1755-1759. 2016.

Conference Proceedings

  1. Mallidi, Sri Harish, and Hynek Hermansky. “Novel neural network based fusion for multistream ASR.” In Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on, pp. 5680-5684. IEEE, 2016.
  2. Ogawa, Tetsuji, Sri Harish Mallidi, Emmanuel Dupoux, Jordan Cohen, Naomi H. Feldman, and Hynek Hermansky. “A new efficient measure for accuracy prediction and its application to multistream-based unsupervised adaptation.” In Pattern Recognition (ICPR), 2016 23rd International Conference on, pp. 2222-2227. IEEE, 2016.
  3. Meyer, Bernd T., Sri Harish Mallidi, Angel Mario Castro Martínez, Guillermo Payá-Vayá, Hendrik Kayser, and Hynek Hermansky. “Performance monitoring for automatic speech recognition in noisy multi-channel environments.” In Spoken Language Technology Workshop (SLT), 2016 IEEE, pp. 50-56. IEEE, 2016.

2015

Conference Proceedings

  1. Sri Harish Mallidi, Tetsuji Ogawa, Hynek Hermansky, Uncertainty estimation of DNN classifiers, Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, Scotsdale, Arizona, December 2015
  2. Roger Hsiao, Jeff Ma, William Hartmann, Martin Karafiat, Frantisek Grezl, Lukas Burget, Igor Szoke, Jan Honza Cernocky, Shinji Watanabe, Zhuo Chen, Sri Harish Mallidi, Hynek Hermansky, Stavros Tsakalidis, Richard Schwartz, Robust Speech Recognition in Unknown Reverberant and Noisy Conditions, Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, Scotsdale, Arizona, December 2015
  3. Sri Harish Mallidi, Tetsuji Ogawa, Karel Vesely, Phani S Nidadavolu, Hynek Hermansky, Autoencoder based multi-stream combination for noise robust speech recognition, Proceedings Interspeech 2015, Dresden, Germany, 2015
  4. Jan Pesan, Lukas Burget, Hynek Hermansky, Karel Vesely, DNN derived filters for processing of modulation spectrum of speech, Proceedings Interspeech 2015, Dresden, Germany, 2015
  5. Hynek Hermansky,Lukáš Burget, Jordan Cohen, Emmanuel Dupoux, Naomi Feldman, John Godfrey, Sanjeev Khudanpur, Matthew Maciejewski, Sri Harish Mallidi, Anjali Menon, Tetsuji Ogawa, Vijayaditya Peddinti, Richard Rose, Richard Stern, Matthew Wiesner, Karel Veselý, “Towards machines that know when they do not know: Summary of work done at 2014 Frederick Jelinek memorial workshop”, Proceedings ICASSP 2015, Brisbane, Australia
Back to top