Kazuki Irie
Note: I completed my PhD in May 2020, and moved to IDSIA.
Kazuki Irie was a PhD student in Computer Science at RWTH Aachen University from May 2014 to March 2020.
His doctoral advisor was Prof. Dr.-Ing. Hermann Ney.
He was a member of the Human Language Technology and Pattern Recognition Group, where he worked on neural network based language modeling to improve automatic speech recognition.
Before joining RWTH Aachen, he studied Applied Mathematics at École Centrale Paris and ENS Cachan in France, and spent a research semester in Operations Research at Georgia Institute of Technology in the USA.
Kazuki Irie's publications at RWTH Aachen University
-
W. Zhou, W. Michel, K. Irie, M. Kitza, R. Schlüter, and H. Ney. The RWTH ASR system for TED-LIUM release 2: Improving Hybrid HMM with SpecAugment. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 7839-7843, Barcelona, Spain, May 2020.
-
K. Irie. Advancing Neural Language Modeling in Automatic Speech Recognition. PhD Thesis, Computer Science Department, RWTH Aachen University, Aachen, Germany, May 2020.
-
A. Gerstenberger, K. Irie, P. Golik, E. Beck, and H. Ney. Domain Robust, Fast, and Compact Neural Language Models. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 7954-7958, Barcelona, Spain, May 2020.
-
K. Irie, A. Gerstenberger, R. Schlüter, and H. Ney. How Much Self-Attention Do We Need? Trading Attention for Feed-Forward Layers. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 6154-6158, Barcelona, Spain, May 2020.
[slides].
-
K. Irie, A. Zeyer, R. Schlüter, and H. Ney. Training Language Models for Long-Span Cross-Sentence Evaluation. In IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 419-426, Sentosa, Singapore, December 2019.
[poster].
-
A. Zeyer, P. Bahar, K. Irie, R. Schlüter, and H. Ney. A comparison of Transformer and LSTM encoder decoder models for ASR. In IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pages 8-15, Sentosa, Singapore, December 2019.
-
K. Irie, A. Zeyer, R. Schlüter, and H. Ney. Language Modeling with Deep Transformers. In Interspeech, pages 3905-3909, Graz, Austria, September 2019.
ISCA Best Student Paper Award. [slides].
-
K. Irie, R. Prabhavalkar, A. Kannan, A. Bruguier, D. Rybach, and P. Nguyen. On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition. In Interspeech, pages 3800-3804, Graz, Austria, September 2019.
[slides].
-
C. Lüscher, E. Beck, K. Irie, M. Kitza, W. Michel, A. Zeyer, R. Schlüter, and H. Ney. RWTH ASR Systems for LibriSpeech: Hybrid vs Attention. In Interspeech, pages 231-235, Graz, Austria, September 2019.
-
K. Beneš, K. Irie, E. Beck, R. Schlüter, and H. Ney. Unsupervised Language Model Adaptation for Speech Recognition with no Extra Resources. In Deutsche Jahrestagung für Akustik (DAGA), pages 954–957, Rostock, Germany, March 2019.
-
K. Irie, Z. Lei, L. Deng, R. Schlüter, and H. Ney. Investigation on Estimation of Sentence Probability By Combining Forward, Backward and Bi-directional LSTM-RNNs. In Interspeech, pages 392-395, Hyderabad, India, September 2018.
-
A. Zeyer, K. Irie, R. Schlüter, and H. Ney. Improved training of end-to-end attention models for speech recognition. In Interspeech, Hyderabad, India, September 2018.
-
K. Irie, S. Kumar, M. Nirschl, and H. Liao. RADMM: Recurrent Adaptive Mixture Model with Applications to Domain Robust Language Modeling. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 6079-6083, Calgary, Canada, April 2018.
[slides].
-
K. Irie, Z. Lei, R. Schlüter, and H. Ney. Prediction of LSTM-RNN Full Context States as a Subtask for N-gram Feedforward Language Models. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 6104-6108, Calgary, Canada, April 2018.
IEEE Spoken Language Processing Student Travel Grant. Best Student Paper Award.
-
R. Schlüter, P. Doetsch, P. Golik, M. Kitza, T. Menne, K. Irie, Z. Tüske, and A. Zeyer. Neuronale Netze in der automatischen Spracherkennung - ein Paradigmenwechsel?. In 44. Jahrestagung für Akustik der Deutschen Gesellschaft für Akustik, pages 15-28, Munich, Germany, March 2018.
-
P. Golik, Z. Tüske, K. Irie, E. Beck, R. Schlüter, and H. Ney. The 2016 RWTH Keyword Search System for Low-Resource Languages. In International Conference Speech and Computer (SPECOM), Lecture Notes in Computer Science, Subseries Lecture Notes in Artificial Intelligence, volume 10458, pages 719-730, Hatfield, UK, September 2017.
-
K. Irie, P. Golik, R. Schlüter, and H. Ney. Investigations on byte-level convolutional neural networks for language modeling in low resource speech recognition. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 5740-5744, New Orleans, LA, USA, March 2017.
-
K. Irie, Z. Tüske, T. Alkhouli, R. Schlüter, and H. Ney. LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition. In Interspeech, pages 3519-3523, San Francisco, CA, USA, September 2016.
-
T. Menne, J. Heymann, A. Alexandridis, K. Irie, A. Zeyer, M. Kitza, P. Golik, I. Kulikov, L. Drude, R. Schlüter, H. Ney, R. Haeb-Umbach, and A. Mouchtaris. The RWTH/UPB/FORTH System Combination for the 4th CHiME Challenge Evaluation. In The 4th International Workshop on Speech Processing in Everyday Environments, pages 39-44, San Francisco, CA, USA, September 2016.
-
R. Schlüter, P. Doetsch, P. Golik, M. Kitza, T. Menne, K. Irie, Z. Tüske, and A. Zeyer. Automatic Speech Recognition Based on Neural Networks. In International Conference Speech and Computer (SPECOM), Lecture Notes in Computer Science, Subseries Lecture Notes in Artificial Intelligence, volume 9811, pages 3-17, Budapest, Hungary, August 2016.
-
Z. Tüske, K. Irie, R. Schlüter, and H. Ney. Investigation on log-linear interpolation of multi-domain neural network language model. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 6005-6009, Shanghai, China, March 2016.
-
K. Irie, R. Schlüter, and H. Ney. Bag-of-Words Input for Long History Representation in Neural Network-based Language Models for Speech Recognition. In Interspeech, pages 2371-2375, Dresden, Germany, September 2015.
-
R. Botros, K. Irie, M. Sundermeyer, and H. Ney. On Efficient Training of Word Classes and Their Application to Recurrent Neural Network Language Models. In Interspeech, pages 1443-1447, Dresden, Germany, September 2015.
-
S. Wiesler, K. Irie, Z. Tüske, R. Schlüter, and H. Ney. The RWTH English lecture recognition system. In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 3322-3326, Florence, Italy, May 2014.
Full list of publications
of the chair.
