Homepage of Matthias Paulik

 

Welcome to my homepage! My name is Matthias Paulik and I work at Cisco's Speech and Language Technology (C-SALT) team, which is part of Cisco's Media Experience and Analytics Business Unit (MXABU), Emerging Technologies Group.

I received my Ph.D. (Dr.-Ing., summa cum laude) degree in Computer Science from Karlsruhe Institute of Technology (KIT), Germany in May 2010. From 2005 to 2010 I was employed as a research assistant at the Carnegie Mellon University location of Interactive Systems Laboratories (interACT research). I also worked (2009-2010) as a research scientist for Mobile Technologies L.L.C., where I was involved in the development of “Jibbigo” – a non-server based speech-to-speech translation software for the iPhone.

My contact information:

Cisco Systems Inc.
855 Tasman Drive, Bldg. 29/1
Milpitas, CA 95035
Phone: +1 408 853 8437
e-mail: mapaulik @ cisco DOT com

 

 


 

Past Research Projects at Interactive Systems Labs (CMU/UKA) and Mobile Technologies

 I was involved in the following research projects:

  • Jibbigo: A speech-to-speech translation software for the iPhone. The first release provided two-way translation between English and Spanish and was targeted for the travel domain. My main responsibilities were the American English and Spanish ASR systems.

  • TRANSTAC: I joined the CMU/ISL TRANSTAC team in fall 2008. I was responsible for the English speech recognition and the user interface / system integration.

  • Open Domain Lecture Translation: I maintained and actively developed the ISL open domain lecture translation system at the US America part of the ISL.

  • GALE: My work within GALE was centered around a tighter coupling of ASR and SMT. In 2007 I mainly worked on sentence segmentation and punctuation recovery for spoken language translation.

  • TC-STAR: Within TC-STAR I was responsible for the development of our spring 2007 evaluation SMT systems for the English-to-Spanish and Spanish-to-English translation tasks. These systems achieved the first rank in several of the benchmarks of the TC-STAR evaluation campain. Further, I developed a Spanish ASR system as it was for example used in [Fuegen07]. I also worked on sentence segmentation and punctuation recovery for Spoken Language Translation from English-to-Spanish.

  • CHIL: In CHIL I mainly worked on language modeling for ASR.

Publications

2011

Leveraging Large Amounts of Loosely Transcribed Corporate Videos for Acoustic Model Training

Matthias Paulik and Panchi Panchapagesan

To appear in Proc. of the Automatic Speech Recognition and Understanding, Big Island, Hawaii, USA, December 2011


Training Speech Translation from Audio Recordings of Interpreter-Mediated Communication

Matthias Paulik and Alex Waibel

To appear in Computer Speech and Language; Available online 10 May 2011


Improving Machine Translation of Spoken Language

Matthias Paulik, Ian Lane and Tanja Schultz

In The GALE Book, Part 3: Machine Translation from Speech, pp. 565-575


2010

Rapid Development of Speech Translation Using Consecutive Interpretation     [pdf]

Matthias Paulik and Alex Waibel

In Proc. of Interspeech, Makuhari, Japan, September 2010


Spoken Language Translation from Parallel Speech Audio: Simultaneous Interpretation as SLT Training Data     [pdf]

Matthias Paulik and Alex Waibel

In Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Dallas, Texas, USA, March 2010


2009

Automatic Translation from Parallel Speech: Simultaneous Interpretation as MT Training Data     [pdf]

Matthias Paulik and Alex Waibel

In Proc. of the Automatic Speech Recognition and Understanding, Merano, Italy, December 2009


2008

Simultaneous Machine Translation of German Lectures into English: Investigating Research Challenges for the Future

Matthias Woelfel, Muntsin Kolss, Florian Kraft, Jan Niehues, Matthias Paulik and Alex Waibel

In Proc. of SLT, Goa, India, December 2008


Simultaneous German-English Lecture Translation

Muntsin Kolss, Matthias Woelfel, Florian Kraft, Jan Niehues, Matthias Paulik and Alex Waibel

In Proc. of IWSLT, Waikiki, Hawaii, October 2008


Ligthly Supervised Acoustic Model Training on EPPS Recordings    [pdf]    [poster]

Matthias Paulik and Alex Waibel

In Proc. of Interspeech, Brisbane, Australia, September 2008

 

Extracting Clues from Human Interpreter Speech for Spoken Language Translation    [pdf]

Matthias Paulik and Alex Waibel

In Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, Nevada, USA, April 2008

 

Sentence Segmentation and Punctuation Recovery for Spoken Language Translation    [pdf]

Matthias Paulik, Sharath Rao, Ian Lane, Stephan Vogel, Tanja Schultz

In Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, Nevada, USA, April 2008

 

System Combination for Machine Translation of Spoken and Written Language    [pdf]

E. Matusov, G. Leusch, R. E. Banchs, N. Bertoldi, D. Dechelotte, M. Federico, M. Kolss, Y. Lee, J. B. Marino, M. Paulik, S. Roukos, H. Schwenk, and H. Ney

IEEE Transactions on Audio, Speech and Language Processing, volume 16, number 7, pages 1222-1237, September 2008

 

 

2007

The ISL Phrase-Based MT System for the 2007 ACL Workshop on Statistical Machine Translation    [pdf]

Matthias Paulik, Kay Rottmann, Jan Niehues, Silja Hildebrand, and Stephan Vogel

In Proc. of the ACL 2007 Second Workshop on Statistical Machine Translation, Prague, Czech Republic, June 23, 2007

 

The Syntax Augmented MT (SAMT) System for the Shared Task in the 2007 ACL Workshop on Statistical Machine Translation    [pdf]

Andreas Zollmann, Ashish Venugopal, Matthias Paulik, and Stephan Vogel

In Proc. of the ACL 2007 Second Workshop on Statistical Machine Translation, Prague, Czech Republic, June 23, 2007

 

Translating language with technology's help    [link to IEEE potentials]

Matthias Paulik, Sebastian Stüker, Christian Fügen, Tanja Schultz, and Alex Waibel

IEEE potentials - the magazine for high-tech inovators, Vol. 26, No.3, pp. 30 - 35, MAY/JUNE 2007

 

 

2006

Open Domain Speech Recognition & Translation: Lectures and Speeches    [pdf]

Christian Fügen, Muntsin Kolss, Matthias Paulik, and Alex Waibel

In Proc. of the TC-STAR Workshop on Speech-to-Speech Translation, Barcelona, Spain, 2006, ELDA

 

The ISL TC-STAR Spring 2006 ASR Evaluation Systems    [pdf]

Sebastian Stüker, Christian Fügen, Roger Hsiao, Shajith Ikbal, Qin Jin, Florian Kraft, Matthias Paulik, Martin Raab, Yik-Cheung Tam, and Matthias Wölfel

In Proc. of the TC-STAR Workshop on Speech-to-Speech Translation, Barcelona, Spain, 2006, ELDA

 

Open Domain Speech Translation: From Seminars and Speeches to Lectures    [pdf]

Christian Fügen, Muntsin Kolss, Matthias Paulik, Sebastian Stüker, Tanja Schultz, and Alex Waibel

Journies d'E'tude sur la Parole (JEP), Invited paper and keynote held by Tanja Schulz, Dinard, France, June 14, 2006

 

Speech Recognition in Human Mediated Translation Scenarios    [pdf]

Matthias Paulik, Sebastian Stüker and Christian Fügen

IEEE Region 8 Student Paper Contest 2006. In Proc. of MELECON, Málaga, Spain, May 2006

 

Open Domain Speech Recognition & Translation: Lectures and Speeches    [pdf]

Christian Fügen, Muntsin Kolss, Dietmar Bernreuther, Matthias Paulik, Sebastian Stüker, Stephan Vogel and Alex Waibel

In Proc. of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France, May 2006

 

 

 

2005

Speech Translation Enhanced Automatic Speech Recognition    [pdf]

Matthias Paulik, Sebastian Stüker, Christian Fügen, Tanja Schultz, Thomas Schaaf and Alex Waibel

In Proc. of the Automatic Speech Recognition and Understanding Workshop (ASRU), San Juan, Puerto Rico, December 2005

 

Document Driven Machine Translation Enhanced ASR    [pdf]

Matthias Paulik, Christian Fügen, Sebastian Stüker, Tanja Schultz, Thomas Schaaf and Alex Waibel

In Proc. of the 9th European Conference on Speech Communication and Technology, Lisbon, Portugal, September 2005

 

 

Diploma Thesis - May 2005

Machine Translation Enhanced Automatic Speech Recognition    [pdf]

Matthias Paulik

Diplomarbeit, Institut für Theoretische Informatik, Universität Karlsruhe, Germany, May 2005