Photo

Dr. Michael Heck

Universitätsstr. 1 Building 25.12, Düsseldorf, Germany 40225
Mail

Hello, I am Michael. I am a postdoctoral researcher in the Dialog Systems and Machine Learning Group at Heinrich Heine University Düsseldorf, Germany, where I work with Milica Gašić. My current research interests revolve around representation learning in the context of dialogue systems.

I graduated with a Doctor of Engineering (D.Eng.) from Nara Institute of Science and Technology (NAIST), Japan in 2018. My doctoral course research interests were acoustic modeling for automatic speech processing, unsupervised learning, representation learning, and other machine learning challenges. For my doctoral thesis, I conducted zero resource speech processing research where I used Bayesian nonparametric methods to tackle the task of unsupervised subword modeling and speech representation learning. My supervisors were Satoshi Nakamura and Sakriani Sakti. From 2018 to 2019 I was Technical Staff in the RIKEN Center for Advanced Intelligence Project (AIP), Tourism Information Analytics (TIA) Team, Japan.

Apart from my current research focus and my doctoral course interests I am experienced in building large scale automatic speech recognition systems, automatic language identification, automatic speech segmentation, among other speech processing related topics.

I graduated from Karlsruhe Institute of Technology (KIT) with a diploma in Informatics (Dipl.-Inform.) after writing my thesis during a scholarship-supported internship period at NAIST. At KIT I worked with Alex Waibel and Sebastian Stüker.

Publications

Articles

Nurul Lubis, Michael Heck, Carel van Niekerk, Milica Gasic
Adaptable Conversational Machines
AI Magazine, 41(3), 28-44, September 2020
(link)

Journals

Michael Heck, Sakriani Sakti, Satoshi Nakamura
Dirichlet Process Mixture of Mixtures Model for Unsupervised Subword Modeling
IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 26, no. 11, July 2018
(link) (pre-print PDF)

Michael Heck, Sakriani Sakti, Satoshi Nakamura
Learning Supervised Feature Transformations on Zero Resources for Improved Acoustic Unit Discovery
In IEICE Transactions on Information and Systems, vol. E101-D, no. 1, January 2018
(link)

International Conferences (peer-reviewed)

Michael Heck, Christian Geishauser, Hsien-Chin Lin, Nurul Lubis, Marco Moresi, Carel van Niekerk, Milica Gasic
Out-of-Task Training for Dialog State Tracking Models
Proceedings of the 28th International Conference on Computational Linguistics (COLING), Online, December 2020
(link) (pre-print)

Nurul Lubis, Christian Geishauser, Michael Heck, Hsien-chin Lin, Marco Moresi, Carel van Niekerk and Milica Gasic
LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization
Proceedings of the 28th International Conference on Computational Linguistics (COLING), Online, December 2020
(link) (pre-print)

Carel van Niekerk, Michael Heck, Christian Geishauser, Hsien-chin Lin, Nurul Lubis, Marco Moresi, Milica Gasic
Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (ENMLP): Findings, Online, November 2020
(link) (pre-print)

Michael Heck, Carel van Niekerk, Nurul Lubis, Christian Geishauser, Hsien-Chin Lin, Marco Moresi, Milica Gasic
TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking
Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDial), 1st Virtual Meeting, July 2020
(link) (talk) (pre-print)

Michael Heck, Sakriani Sakti, Satoshi Nakamura
Feature Optimized DPGMM Clustering for Unsupervised Subword Modeling: A Contribution to ZeroSpeech 2017
Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Naha, Japan, December 2017
(link, sign-in required)

Nurul Lubis, Michael Heck, Sakriani Sakti, Koichiro Yoshino, Satoshi Nakamura
Processing Negative Emotions Through Social Communication: Multimodal Database Construction and Analysis
Proceedings of the International Conference on Affective Computing and Intelligent Interaction (ACII), San Antonio, USA, October 2017
(link)

Michael Heck, Masayuki Suzuki, Takashi Fukuda, Gakuto Kurata, Satoshi Nakamura
Ensembles of Multi-scale VGG Acoustic Models
Proceedings of Interspeech, Stockholm, Sweden, August 2017
(link)

Michael Heck, Sakriani Sakti, Satoshi Nakamura
Iterative Training of a DPGMM-HMM Acoustic Unit Recognizer in a Zero Resource Scenario
Proceedings of the IEEE Workshop on Spoken Language Technology (SLT), San Diego, USA, December 2016
(link, sign-in required)

Michael Heck, Sakriani Sakti, Satoshi Nakamura
Supervised Learning of Acoustic Models in a Zero Resource Setting to Improve DPGMM Clustering
Proceedings of Interspeech, San Francisco, USA, September 2016
(link)

Michael Heck, Sakriani Sakti, Satoshi Nakamura
Unsupervised Linear Discriminant Analysis for Supporting DPGMM Clustering in the Zero Resource Scenario
Proceedings of the Workshop on Spoken Language Technology for Under-resourced Languages (SLTU), Yogyakarta, Indonesia, May 2016
(link)

Quoc Truong Do, Michael Heck, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura
The NAIST ASR System for the 2015 Multi-genre Broadcast Challenge: On Combination of Deep Learning Systems Using a Rank-score Function
Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, USA, December 2015
(link)

Michael Heck, Quoc Truong Do, Sakriani Sakti, Graham Neubig, Satoshi Nakamura
The NAIST English Speech Recognition System for IWSLT 2015
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Da Nang, Vietnam, December 2015
(link)

Kevin Kilgour, Michael Heck, Markus Müller, Matthias Sperber, Sebastian Stüker, Alex Waibel
The 2014 KIT IWSLT Speech-to-Text Systems for English, German and Italian
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Lake Tahoe, USA, December 2014
(link)

Michael Heck, Sebastian Stüker, Sakriani Sakti, Alex Waibel, Satoshi Nakamura
Incremental Unsupervised Training for University Lecture Recognition
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Heidelberg, Germany, December 2013
(link)

Kevin Kilgour, Christian Mohr, Michael Heck, Quoc Bao Nguyen, Van Huy Nguyen, Evgeniy Shin, Igor Tseyer, Jonas Gehring, Markus Müller, Matthias Sperber, Sebastian Stüker, Alex Waibel
The 2013 KIT IWSLT Speech-to-Text Systems for German and English
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Heidelberg, Germany, December 2013
(link)

Michael Heck, Christian Mohr, Sebastian Stüker, Markus Müller, Kevin Kilgour, Jonas Gehring, Quoc Bao Nguyen, Van Huy Nguyen, Alex Waibel
Segmentation of Telephone Speech Based on Speech and Non-Speech Models
Proceedings of the International Conference on Speech and Computer (SPECOM), Plzen, Czech Republic, September 2013
(link)

Michael Heck, Sebastian Stüker, Alex Waibel
A Hybrid Phonotactic Language Identification System with an SVM Back-end for Simultaneous Lecture Translation
Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March 2012
(link)

Michael Heck, Keigo Kubo, Matthias Sperber, Sakriani Sakti, Sebastian Stüker, Christian Saam, Kevin Kilgour, Christian Mohr, Graham Neubig, Tomoki Toda, Satoshi Nakamura, Alex Waibel
The KIT-NAIST (Contrastive) English ASR System for IWSLT 2012
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Hong Kong, December 2012
(link)

Christian Saam, Christian Mohr, Kevin Kilgour, Michael Heck, Matthias Sperber, Keigo Kubo, Sebastian Stüker, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura, Alex Waibel
The 2012 KIT and KIT-NAIST English ASR Systems for the IWSLT Evaluation
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Hong Kong, December 2012
(link)

Jan Niehues, Mohammed Mediani, Teresa Herrmann, Michael Heck, Christian Herff, Alex Waibel
The KIT Translation system for IWSLT 2010
Proceedings of the International Workshop on Spoken Language Translation (IWSLT), Paris, France, December 2010
(link)

Sebastian Stüker, Michael Heck, Katja Renner, Alex Waibel
Spoken News Queries over the World Wide Web
Proceedings of the International Workshop on Searching Spontaneous Conversational Speech (SSCS), Firenze, Italy, October 2010
(link)

Theses

Michael Heck
Unsupervised Representation Learning and Acoustic Modeling in the Zero Resource Scenario
Doctoral Thesis, September 2018
(link)

Michael Heck
Unsupervised Acoustic Model Training for Simultaneous Lecture Translation in Incremental and Batch Mode
Diploma Thesis, December 2012
(link)

Michael Heck
Automatic Language Identification for Natural Language Processing Systems
Student Research Project Thesis („Studienarbeit“), August 2011
(link)
Michael Heck © 2021