portrait



Tim Schlippe
Dr.-Ing.





E-mail: speech at research-karlsruhe.de



            Research multilingual speech processing; multilingual speech recognition; web-based tools for the development of speech processing systems; rapid adaptation of speech recognition systems to new languages and domains; language modeling in the context of code-switching; statistical machine translation; pronunciation modeling; crowdsourcing; human-computer interfaces; voice driven type design.

            Publications

Voice Driven Type Design,
Matthias Wölfel, Tim Schlippe, and Angelo Stitz
In Proceedings of The 8th International Conference on Speech Technology and Human-Computer Dialog (SpeD 2015), Bucharest, Romania, 14-17 October 2015.
Paper          Presentation           bibtex

           

A Voice Driven Type Design Demo,
Matthias Wölfel, Angelo Stitz, and Tim Schlippe,
Demo Session of Mensch & Computer (MuC 2015), Stuttgart, Germany, 6-9 September 2015.
Paper          Presentation           bibtex

           

Voice Driven Type Design,
Matthias Wölfel, Angelo Stitz, and Tim Schlippe,
GLOBALE: Infosphere, ZKM (Center for Art and Media), Karlsruhe, Germany, 5 September 2015 - 31 January 2016.
Brochure                                  bibtex

           

Cross-lingual Lexical Language Discovery from Audio Data Using Multiple Translations,
Felix Stahlberg, Tim Schlippe, Stephan Vogel, and Tanja Schultz,
In Proceedings of The 40th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015), Brisbane, Australia, 19-24 April 2015.
Paper          Presentation           bibtex

           

Rapid Generation of Pronunciation Dictionaries for new Domains and Languages,
Tim Schlippe
KIT Library, December 2014.
Dissertation                              bibtex

           

Word Segmentation and Pronunciation Extraction from Phoneme Sequences Through Cross-Lingual Word-to-Phoneme Alignment,
Felix Stahlberg, Tim Schlippe, Stephan Vogel, and Tanja Schultz,
In Computer Speech & Language, Elservier, 18 October 2014.
Paper                                       bibtex

           

Methods for Efficient Semi-Automatic Pronunciation Dictionary Bootstrapping,
Tim Schlippe, Matthias Merz, and Tanja Schultz,
In Proceedings of The 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), Singapore, 14-18 August 2014.
Paper          Presentation           bibtex

           

BioKIT - Real-time Decoder For Biosignal Processing,
Dominic Telaar, Michael Wand, Dirk Gehrig, Felix Putze, Christoph Amma, Dominic Heger, Ngoc Thang Vu, Mark Erhardt, Tim Schlippe, Matthias Janke, Christian Herff, and Tanja Schultz,
In Proceedings of The 15th Annual Conference of the International Speech Communication Association (Interspeech 2014), Singapore, 14-18 August 2014.
Paper          Poster           bibtex

           

GlobalPhone: Pronunciation Dictionaries in 20 Languages,
Tanja Schultz and Tim Schlippe,
In Proceedings of The 9th edition of the Language Resources and Evaluation Conference (LREC 2014), Reykjavik, Iceland, 26-31 May 2014.
Paper          Poster           bibtex

           

Combining Grapheme-to-Phoneme Converter Outputs for Enhanced Pronunciation Generation in Low-Resource Scenarios,
Tim Schlippe, Wolf Quaschningk, and Tanja Schultz,
In Proceedings of The 4th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU 2014), St. Petersburg, Russia, 14-16 May 2014.
Paper          Presentation           bibtex

           

Automatic Detection of Anglicisms for the Pronunciation Dictionary Generation: A Case Study on our German IT Corpus,
Sebastian Leidig, Tim Schlippe, and Tanja Schultz,
In Proceedings of The 4th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU 2014), St. Petersburg, Russia, 14-16 May 2014.
Paper          Presentation           bibtex

           

Towards Automatic Speech Recognition without Pronunciation Dictionary, Transcribed Speech and Text Resources in the Target Language using Cross-Lingual Word-to-Phoneme Alignment,
Felix Stahlberg, Tim Schlippe, Stephan Vogel, and Tanja Schultz,
In Proceedings of The 4th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU 2014), St. Petersburg, Russia, 14-16 May 2014.
Paper          Presentation           bibtex

           

Features for Factored Language Models for Code-Switching Speech,
Heike Adel, Kartin Kirchhoff, Dominic Telaar, Ngoc Thang Vu, Tim Schlippe, and Tanja Schultz,
In Proceedings of The 4th Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU 2014), St. Petersburg, Russia, 14-16 May 2014.
Paper          Presentation           bibtex

           

Web-based Tools and Methods for Rapid Pronunciation Dictionary Creation,
Tim Schlippe, Sebastian Ochs, and Tanja Schultz,
Speech Communication, vol. 56, pp. 101 -– 118, Elservier, January 2014.
Paper                                      bibtex

           

Unsupervised Language Model Adaptation for Automatic Speech Recognition of Broadcast News Using Web 2.0,
Tim Schlippe, Lukasz Gren, Ngoc Thang Vu, and Tanja Schultz,
In Proceedings of The 14th Annual Conference of the International Speech Communication Association (Interspeech 2013), Lyon, France, 25-29 August 2013.
Paper          Presentation           bibtex

           

Pronunciation Extraction from Phoneme Sequences through Cross-Lingual Word-to-Phoneme Alignment,
Felix Stahlberg, Tim Schlippe, Stephan Vogel, and Tanja Schultz,
In Proceedings of The 1st International Conference on Statistical Language and Speech Processing (SLSP 2013), Tarragona, Spain, 29-31 July 2013.
Paper          Presentation           bibtex

           

Rapid Bootstrapping of a Ukrainian Large Vocabulary Continuous Speech Recognition System,
Tim Schlippe, Mykola Volovyk, Kateryna Yurchenko, and Tanja Schultz,
In Proceedings of The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), Vancouver, Canada, 26-31 May 2013.
Paper          Poster           bibtex

           

GlobalPhone: A Multilingual Text & Speech Database in 20 Languages,
Tanja Schultz, Ngoc Thang Vu, and Tim Schlippe,
In Proceedings of The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), Vancouver, Canada, 26-31 May 2013.
Paper          Poster           bibtex

           

Recurrent Neural Network Language Modeling for Code Switching Conversational Speech,
Heike Adel, Ngoc Thang Vu, Franziska Kraus, Tim Schlippe, Haizhou Li, and Tanja Schultz,
In Proceedings of The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), Vancouver, Canada, 26-31 May 2013.
Paper          Poster           bibtex

           

Statistical Machine Translation based Text Normalization with Crowdsourcing,
Tim Schlippe, Chenfei Zhu, Daniel Lemcke, and Tanja Schultz,
In Proceedings of The 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), Vancouver, Canada, 26-31 May 2013.
Paper          Poster           bibtex

           

Word Segmentation through Cross-Lingual Word-to-Phoneme Alignment,
Felix Stahlberg, Tim Schlippe, Stephan Vogel, and Tanja Schultz,
In Proceedings of The Fourth IEEE Workshop on Spoken Language Technology (SLT 2012), Miami, Florida, 2-5 December 2012.
Paper          Poster           bibtex

           

Automatic Error Recovery for Pronunciation Dictionaries,
Tim Schlippe, Sebastian Ochs, Ngoc Thang Vu, and Tanja Schultz,
In Proceedings of The 13th Annual Conference of the International Speech Communication Association (Interspeech 2012), Portland, Oregon, 9-13 September 2012.
Paper          Poster           bibtex

           

Hausa Large Vocabulary Continuous Speech Recognition,
Tim Schlippe, Edy Guevara Komgang Djomgang, Ngoc Thang Vu, Sebastian Ochs, and Tanja Schultz,
In Proceedings of The 3rd Workshop on Spoken Language Technologies for Under-resourced Languages (SLTU 2012), Cape Town, South Africa, 7-9 May 2012.
Paper          Presentation           bibtex

           

Grapheme-to-Phoneme Model Generation for Indo-European Languages,
Tim Schlippe, Sebastian Ochs, and Tanja Schultz,
In Proceedings of The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), Kyoto, Japan, 25-30 March 2012.
Paper          Poster           bibtex

           

A First Speech Recognition System For Mandarin-English Code-Switch Conversational Speech,
Ngoc Thang Vu, Dau-Cheng Lyu, Jochen Weiner, Dominic Telaar, Tim Schlippe, Fabian Blaicher, Eng-Siong Chng, Tanja Schultz, and Haizhou Li,
In Proceedings of The 37th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), Kyoto, Japan, 25-30 March 2012.
Paper          Poster           bibtex

           

Speech Recognition for Machine Translation in Quaero,
Lori Lamel, Sandrine Courcinous, Julien Despres, Jean-Luc Gauvain, Yvan Josse, Kevin Kilgour, Florian Kraft, Le Viet Bac, Hermann Ney, Markus Nußbaum-Thom, Ilya Oparin, Tim Schlippe, Ralf Schlüter, Tanja Schultz, Thiago Fraga Da Silva, Sebastian Stüker, Martin Sundermeyer, Bianca Vieru, Ngoc Thang Vu, Alexander Waibel, and Cécile Woehrling,
In Proceedings of The International Workshop on Spoken Language Translation (IWSLT 2011), San Francisco, USA, 8-9 December 2011.
Paper      Presentation      bibtex

           

Wiktionary as a Source for Automatic Pronunciation Extraction,
Tim Schlippe, Sebastian Ochs, and Tanja Schultz,
In Proceedings of The 11th Annual Conference of the International Speech Communication Association (Interspeech 2010), Makuhari, Japan, 26-30 September 2010.
Paper      Presentation      bibtex

           

Rapid Bootstrapping of five Eastern European Languages using the Rapid Language Adaptation Toolkit,
Ngoc Thang Vu, Tim Schlippe, Franziska Kraus, and Tanja Schultz,
In Proceedings of The 11th Annual Conference of the International Speech Communication Association (Interspeech 2010), Makuhari, Japan, 26-30 September 2010
Paper          Poster           bibtex

           

Text Normalization based on Statistical Machine Translation and Internet User Support,
Tim Schlippe, Chenfei Zhu, Jan Gebhardt, and Tanja Schultz,
In Proceedings of The 11th Annual Conference of the International Speech Communication Association (Interspeech 2010), Makuhari, Japan, 26-30 September 2010.
Paper          Poster           bibtex

           

Diacritization as a Translation Problem and as a Sequence Labeling Problem,
Tim Schlippe, ThuyLinh Nguyen, and Stephan Vogel,
In Proceedings of The Eighth Conference of the Association for Machine Translation in the Americas (AMTA 2008), Waikiki, Hawai'i, USA, 21-25 October 2008.
Paper      Presentation      bibtex

            Projects at KIT

RLAT
RLAT stands for Rapid Language Adaptation Toolkit and is a continuation of the SPICE sytem which has been developed between 2004 and 2007.
Speech technology potentially allows everyone to participate in today's information revolution and can bridge the language barrier gap. Unfortunately, construction of speech processing systems requires significant resources. With some 6,900 languages in the world, traditionally speech processing is prohibitive to all but the most economically viable languages. In spite of recent improvements in speech processing, supporting new languages is a skilled job requiring significant effort from trained individuals. RLAT aims to overcome both limitations by providing an interactive language creation and evaluation toolkit that allows everyone to develop speech processing models, to collect appropriate data for model building, and to evaluate the results enabling iterative improvements.
Knowledge and data are shared between recognition and synthesis such as phoneme sets, pronunciation dictionaries, acoustic models, and text resources. User studies are applied to indicate how well speech systems can be build, how well tools support their efforts and what must be improved to create even better systems.
(according to http://csl.ira.uka.de/spice)
For more information about RLAT see http://csl.ira.uka.de/rlat-dev.

           

Quaero
Quaero (Latin: I seek) is a collaborative research and development program, centered at developing multimedia and multilingual indexing and management tools for professional and general public applications such as the automatic analysis, classification, extraction and exploitation of information.
The research aims to facilitate the extraction of information in unlimited quantities of multimedia and multilingual documents, including written texts, speech and music audio files, and images and videos.
Quaero was created to respond to new needs for the general public and professional use, and new challenges in multimedia content analysis resulting from the explosion of various information types and sources in digital form, available to everyone via personal computers, television and handheld terminals.
(according to www.quaero.org)
For more information about Quaero see http://www.quaero.org.

           

GlobalPhone
GlobalPhone is an ongoing database collection that provides transcribed speech data for the development and evaluation of large speech processing systems in the most widespread languages of the world.
GlobalPhone is designed to be uniform across languages with respect to the amount of text and audio data per language, the audio data quality (microphone, noise, channel), the collection scenario (task, setup, speaking style etc.), and the transcription conventions and supplies an excellent basis for research in the areas of (1) multilingual speech recognition, (2) rapid deployment of speech processing systems to new languages, (3) language and speaker identification tasks, (4) monolingual speech recognition in a large variety of languages, as well as (5) comparisons across major languages based on text and speech data.

           

Code-Switch
Code-Switch is a project funded by Temasec Labs at NTU (Nanyang Technological University) in Singapore, headed by Prof. Dr. Haizhou Li.
In this project we investigate multilingual code-switch continuous speech recognition for large vocabularies. Code-switching is a phenomenon where more than one language or dialect is used in a conversation. Code-switching can occur between sentences (inter-sentential) or within a sentence (intra-sentential). Our research aims at developing an automatic speech recognition system which can handle both, inter and intra-sentential code-switching in conversational speech.
The scope of the research includes data preparation, multilingual acoustic modeling, multilingual pronunciation modeling, multilingual language modeling, as well as automatic code-switch detection, and finally the recognition of code-switch conversational speech.

            Teaching at KIT

Lecture "Multilinguale Mensch-Maschine Kommunikation" (Multilingual Human-Machine Interaction)
(SS 2009, SS 2010, SS 2011, SS 2012, SS 2013)

Practical course "Multilingual Speech Processing"
(WS 2009/2010, WS 2010/2011, WS 2011/2012, WS 2012/2013)

Seminar "Aktuelle Themen der Sprachverarbeitung" (State-of the-Art Topics in Automatic Speech Processing)
(WS 2010/11)