Tanja Schultz

Business Address: Language Technologies Institute

    Carnegie Mellon University

5000 Forbes Avenue

Pittsburgh, PA 15213-3890

Phone: (412) 268 8616

Fax: (412) 268 5578

Email: tanja@cs.cmu.edu

Homepage: http://www.cs.cmu.edu/~tanja

Education

Since July 2002

Research Scientist / Assistant Professor

Language Technologies Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania USA

2000-2002

Research Associate / Post Doctoral Fellow

Language Technologies Institute, Interactive Systems Laboratories, Carnegie Mellon University, Pittsburgh, Pennsylvania USA

1995-2000

Graduate Research Assistant / PhD Student

University of Karlsruhe, Karlsruhe, Germany

PhD in Computer Science

Dissertation Title: Language Independent and Language Adaptive Speech Recognition (Multilinguale Spracherkennung – Kombination akustischer Modelle zur Portierung auf neue Sprachen)

Advisor: Prof. Dr. Alex Waibel, Co-Advisor: Prof. Dr. Dirk van Compernolle

1990-1995

Diploma degree in Computer Science

University of Karlsruhe, Karlsruhe, Germany

Diploma thesis: Language Identification (Identifizierung von Sprachen – Exemplarisch aufgezeigt am Beispiel der Sprachen Deutsch, Englisch und Spanisch)

Advisors: Prof. Dr. Alex Waibel and Dr. I. Rogina

1983-1989

Masters in Mathematics (07/1989)

Masters in Sport, Physical Education, and Educational Science (11/1989)

University of Heidelberg, Heidelberg, Germany

Masters thesis: DieBedeutung der Normierung für die praxisnahe Gestaltung sportmotorischer Tests.

Advisor: Prof. Dr. Klaus Bös

Educational Awards and Honors

2001: FZI Award for an outstanding dissertation in Computer Science

2002: Allen Newell Medal for Research Excellence in Speech-to-Speech Machine Translation

Employment

Since July 2002

Research Scientist / Assistant Professor

Language Technologies Institute, Interactive Systems Laboratories

Carnegie Mellon University, Pittsburgh, PA

2000-2002

Research Associate / Post Doctoral Fellow

Language Technologies Institute, Interactive Systems Laboratories

Carnegie Mellon University, Pittsburgh, PA

Teaching courses and labs in speech recognition and understanding; Advising/Coadvising Masters papers and Ph.D. theses; Conducting research on multilingual speech recognition and automatic pronunciation dictionary generation; In charge of research on conversational meeting and telephone speech, dialogue systems, as well as speaker, language, and accent identification; Administrative responsibilities in admissions committee.

1995-2000

Graduate Research Assistant

Institut für Logik, Komplexität und Deduktionssystems, Department of Computer Science, Interactive Systems Laboratories, University of Karlsruhe, Germany.

Co-teaching seminars and labs in speech recognition, Coadvising independent studies and Masters theses; Conducting research on large vocabulary speech recognition in many different languages, multilingual acoustic modeling, spontaneous speech recognition, language identification, acoustic and language modeling of human and non-human noises; Module-coordinator for Karlsruhe University in the Verbmobil-2 project.

1993-1995

Undergraduate Research Assistant

Institut für Logik, Komplexität und Deduktionssystems, Department of Computer Science, Interactive Systems Laboratories, University of Karlsruhe, Germany.

Research on speech recognition on spontaneously spoken English and German speech directed by senior members of the lab. Involved in research and evaluations in the Verbmobil-1 project.

1990-1994

Consultant and Instructor

Institut für Sport und Sportwissenschaft, University of Heidelberg, Germany.

Teaching courses in electronic data managements and statistical methods. Consulting Masters and P.hD. students to conduct research in social science, and adequate usage of statistical methods.

1988-1990

Consultant

University Children’s Hospital, University of Heidelberg, Germany.

Conducting research on pulmonary lunge function of children. Consultant for medical studies on pediatric asthma and cystic fibrosis patients.

1985-1989

Undergraduate Research Assistant

Institut für Sport und Sportwissenschaft, University of Heidelberg, Germany.

Involved in research on design and development of tests for athlete’s motoric functions and their long-term study. Implementation of statistical methods and evaluation of the developed tests.

Research Goals

General Research Goals

My fundamental research goal is to reveal techniques and algorithms that are
necessary in order to construct automatic speech recognition systems that can
robustly function in multilingual environments and applications. I believe that
automatic speech recognition

engines are the most natural front-end for applications which allow communication

across language and culture barriers. Since it is my wish to build a bridge across

these borders, I want to provide a significant scientific contribution to reach this

goal. Another focus of my attention is the rapid deployment of speech recognizers
in new tasks and languages. The massive reduction of effort in terms of time and

costs is necessary to speed up the develop-ment of recognizers in new tasks and

languages. It is my belief that this is an essential prerequisite in order to make

speech-driven applications attractive and available to the public and also to

include speakers of languages in or which only few no resources are available. I also

have a great interest in the identification of non-verbal cues from speech such as

emotion, focus of attention, spoken accent and language, and other kinds of

information about the speaker. Finally, I would like to investigate the potential of

modeling speech as a function of articulatory gestures especially in the context of

language independency.

Future Plans

The focus of my research in the next several years will be on (1) rapid deployment of

automatic speech recognition for minority languages; (2) speaker, accent, and

language identification; and (3) speech recognition using articulatory features.

(1) Rapid Deployment of ASR for Minority Languages (funded under the AVENUE

project):

Today’s speech recognition systems require huge amounts of audio and text data in

order to reliable train the necessary knowledge sources such as acoustic and language

models. These requirements prohibit the development of speech-driven applications

for small language communities since they usually cannot provide such large resources.

It is therefore absolutely vital to drastically reduce the amount of development data

so that speakers of minority languages are not disfranchised or forced to abandon their

cultural and linguistic heritage. Our approach to rapid development of Automatic

Speech Recognizers involves (1) Language adaptive acoustic models, (2)

Generating pronunciations for large vocabulary, and (3) Language Modeling with

limited data. For the first part we plan to estimate acoustic models for minority

languages by borrowing data from various source languages for which such data is

more plentiful, while using only very limited amounts of adaptation data from the

minority language. For the generation of pronunciation dictionaries, we propose to

apply several phone recognizers on different languages to decode words from the

language in questions. Using IPA mappings from the source to the target language

will be used to find a consensus among the recognizers. This consensus is likely

to be close to the actual pronunciation of the target word. For language modeling, we

are planning to counterbalance the lack of text data by a combination of text

accumulation from various resources, generating text from grammar rules,

class-based language models, and model interpolation.

(2) Speaker, Accent, and Language Identification (submitted under the USAID

project):

Speech is a much richer form of communication than text. It contains numerous cues that are not lexical in nature and do not require reliable transcripts from a time consuming

speech-to-text procedure to trigger language dependent devices, retrieve, describe or

search for critical information. To access information of this nature requires derivation of

meta-level information from the signal. In the proposed work, we will develop

algorithms and techniques that provide these non-verbal cues to identify a speaker as

well as the spoken language and accent. We intend to expand our focus to the problem that the speakers might not be cooperative users, but are rather highly uncooperative ones.

Other methods we intend to explore include the use of multilingual phone string

sequences, hierarchical speaker modeling, and the use of explicit data transforms to

correct for microphone distance and angle. Finally, online learning, in which test data

classified with high confidence is added to the training set, should allow

incremental performance improvements across channel conditions. My primary

contribution will be the identification of speaker, accent, and language using the

multilingual phone string approach.

(3) Articulatory Features (submitted under the SPINE project):

Speech recognition systems today are still, fundamentally, template-based

matching systems that model words as a sequence of phonetic units whose acoustic

models are trained beforehand. This works quite well when the scenario allows

the collection of appropriate training data for the models, and the assumption

holds that variations in speech can be described by operations such as

deletions, insertions, and substitutions of phonetic units. It is already known

that conversational speech and speech in noisy environments bears little

resemblance to the canonical phonetic form and that it is subject to significant

durational and prosodic variation. Thus, it cannot be described properly by

sequences of phones but only by loosely coupled parallel streams of articulatory

gestures. We therefore propose to achieve invariance across the sources of

variability by (a) Modeling of the articulatory production rather than the

patterns it produces, and (b) Make use of adaptation at all levels to handle

varying environments, speaking styles and emotions. Specifically, we will develop

recog-nizers using asynchronous streams of articulatory features that degrade more

naturally under deletions and reductions in speech. In my opinion, articulatory features

have a large potential for language independent speech recognition since they (1) model

speech as a function of articulators which are uniform across human beings not matter

which language is spoken, and (2) are limited in number, thus less confusable than

phones and easier to cover.

Publication List

Book:

2001 Tanja Schultz, Multilinguale Spracherkennung: Kombination akustischer Modelle zur Portierung auf neue Sprachen. Berichte aus der Informatik, Aachen: Shaker Verlag, 2001.

Book Chapters:

2001 Susanne Jekat and Tanja Schultz, Evaluation sprachverarbeitender Systeme. Einführung in die Computerlinguistik, Springer Verlag.

2000 Alex Waibel, Hagen Soltau, Tanja Schultz, Thomas Schaaf, and Florian Metze, Multilingual Speech Recognition. Verbmobil: Foundations of Speech-to-Speech Translation, Wolfgang Wahlster (Ed.), Springer Verlag, 2000.

Invited and Refereed Journal Contributions:

2001 Tanja Schultz and Alex Waibel, Language Independent and Language Adaptive Acoustic Modeling. Speech Communication, Volume 35, Issue 1-2, pp 31-51, August 2001.

2000 Alex Waibel, Petra Geutner, Laura Mayfield-Tomokiyo, Tanja Schultz, and Monika Woszczyna, Multilinguality in Speech and Spoken Language Systems. Proceedings of the IEEE, Special Issue on Spoken Language Processing, Volume 88 (8), pp 1297-1313, August 2000.

1997 Karl Paul and Tanja Schultz, Evaluation of a pocket-sized turbine spirometer for clinical use with children. Respiratory Medicine 1997; 91: 369-372.

Conference Proceedings:

2002 Qin Jin, Tanja Schultz, and Alex Waibel, Speaker Identification using Multilingual Phone Strings. To be presented in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2002), Orlando, Florida, May 2002.

2002 Bing Zhao and Tanja Schultz, Discriminative Training of Parametric Trajectory Models for Speech Recognition. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2002), Orlando, Florida, May 2002.

2002 Tanja Schultz, Qin Jin, Kornel Laskowski, Alicia Tribble, and Alex Waibel, Speaker, Accent, and Language Identification using Multilingual Phone Strings. Proceedings of the Human Language Technology Meeting (HLT-2002), San Diego, March 2002.

2002 Florian Metze, John McDonough, Hagen Soltau, Chad Langley, Alon Lavie, Tanja Schultz, Alex Waibel, Roldano Cattoni, Gianni Lazzari, and Fabio Pianesi, The NESPOLE! Speech-to-Speech Translation System. Proceedings of the Human Language Technology Meeting (HLT-2002), San Diego, March 2002.

2002 Florian Metze, John McDonough, Hagen Soltau, Alon Lavie, Lori Levin, Chad Langley, Tanja Schultz, Alex Waibel, Roldano Cattoni, Gianni Lazzari, Nadia Mana, Fabio Pianesi, and Emanuelle Pianta, Enhancing the Usability and Performance of NESPOLE!: a Real-World Speech-to-Speech Translation System. Proceedings of the Human Language Technology Meeting (HLT-2002), San Diego, March 2002.

2001 Christian Fügen, Martin Westphal, Mike Schneider, Tanja Schultz, and Alex Waibel, LingWear: A Mobil Tourist Information System. Proceedings of the Human Language Technology Meeting (HLT-2001), San Diego, March 2001.

2001 Alex Waibel, Hua Yue, Hagen Soltau, Tanja Schultz, Thomas Schaaf, Yue Pan, Florian Metze, and Michael Bett, Advances in Meeting Recognition. Proceedings of the Human Language Technology Meeting (HLT-2001), San Diego, March 2001.

2001 Alon Lavie, Lori Levin, Tanja Schultz, and Alex Waibel, Domain Portability in Speech-to-Speech Translation. Proceedings of the Human Language Technology Meeting (HLT-2001), San Diego, March 2001.

2001 Alex Waibel, Michael Bett, Klaus Ries, Thomas Schaaf, Tanja Schultz, Hagen Soltau, Hua Yu, and Klaus Zechner, Advances in Automatic Meeting Record Creation and Access. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2001), Salt Lake City, May 2001.

2001 Tanja Schultz, Alex Waibel, Michael Bett, Florian Metze, Yue Pan, Klaus Ries, Thomas Schaaf, Hagen Soltau, Martin Westphal, Hua Yu, and Klaus Zechner, The ISL Meeting Room System. Proceedings of the Workshop on Hands-Free Speech Communication (HSC-2001), Kyoto Japan, April 2001.

2000 Akira Kurematsu, Youichi Akegami, Susanne Burger, Susanne Jekat, Brigitte Lause, Victoria MacLaren, Daniela Oppermann, and Tanja Schultz, Verbmobil Dialogues: Multifaced Analysis. Proceedings of the International Conference of Spoken Language Processing (ICSLP-2000), Beijing, China, October 2000.

2000 Tanja Schultz and Alex Waibel, Language Portability in Acoustic Modeling. Proceedings of the Workshop on Multilingual Speech Communication (MSC-2000), pp 59-64, Kyoto, Japan, October 2000.

2000 Tanja Schultz and Alex Waibel, Polyphone Decision Tree Specialization for Language Adaptation. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2000), Istanbul, Turkey, June 2000.

2000 Florian Metze, Thomas Kemp, Thomas Schaaf, Tanja Schultz, and Hagen Soltau, Confidence Measure based Language Identification. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2000), Istanbul, Turkey, June 2000.

2000 Kenan Çarki, Petra Geutner, and Tanja Schultz, Turkish LVCSR: Towards better Speech Recognition for Agglutinative Languages. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2000), Istanbul, Turkey, June 2000.

1999 Tanja Schultz and Alex Waibel, Language adaptive LVCSR through Polyphone Decision Tree Specialization. Workshop on Multi-lingual Interoperability in Speech Technology (MIST-1999), pp 85--90, Leusden, The Netherlands, September 1999.

1999 Jürgen Reichert, Tanja Schultz, and Alex Waibel, Mandarin Large Vocabulary Speech Recognition using the GlobalPhone Database. Proceedings of the 6^th European Conference on Speech Communication and Technology (Eurospeech-1999), pp 815--818, Budapest, Hungary, September 1999.

1999 Daniel Kiecza, Tanja Schultz, and Alex Waibel, Data-Driven Determination of Appropriate Dictionary Units for Korean LVCSR. Proceedings of the International Conference on Speech Processing (ICSP-1999), pp 323--327, Seoul, Korea, August 1999.

1999 Akira Kurematsu, Youichi Akegami, Tanja Schultz, and Susanne Burger, Development of Data Collection and Transliteration of Japanese Spontaneous Database in the Travel Arrangement Task Domain. International Workshop on East-Asian Language Resources and Evaluation (Oriental COCOSDA-1999), Taipei, Taiwan, May 1999.

1999 Tanja Schultz and Alex Waibel, Experiments towards a Multi-language LVCSR Interface. Proceedings of the 2^nd International Conference on Multi-modal Interfaces (ICMI-1999), Hong Kong, China, January 1999.

1998 Tanja Schultz and Alex Waibel, Language Independent and Language Adaptive Large Vocabulary Speech Recognition. Proceedings of the International Conference of Spoken Language Processing (ICSLP-1998), Vol. 5 pp 1819--1822, Sydney, Australia, November 1998.

1998 Martin Westphal, Tanja Schultz, and Alex Waibel, Linear Discriminant - A New Criterion for Speaker Normalization. Proceedings of the International Conference of Spoken Language Processing (ICSLP-1998), Vol. 3 pp 827--830, Sydney, Australia, November 1998.

1998 Tanja Schultz and Alex Waibel, Adaptation of Pronunciation Dictionaries for Recognition of Unseen Languages, Workshop on Speech and Communication (SPECOM-1998), pp 207--210, St.Petersburg, Russia, October 1998.

1998 Tanja Schultz and Alex Waibel, Das Projekt GlobalPhone: Multilinguale Spracherkennung. Computers, Linguistics, and Phonetics between Language and Speech Proceedings of the 4th Conference on NLP (KONVENS-1998), pp 179--189, Bonn, Germany, October 1998.

1998 Tanja Schultz and Alex Waibel, Development of Multilingual Acoustic Models in the GlobalPhone Project. Proceedings of the 1^st Workshop on Text, Speech, and Dialogue (TSD-1998), pp 311--316, Brno, Czech Republic, September 1998.

1998 Hagen Soltau, Tanja Schultz, Martin Westphal, Alex Waibel, Recognition of Music Types. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-1998), Seattle, WA, May 1998.

1998 Tanja Schultz and Alex Waibel, Multilingual and Crosslingual Speech Recognition. Proceedings of the DARPA Workshop on Broadcast News Transcription and Understanding, pp 259--262, Lansdowne, VA, February 1998.

1997 Tanja Schultz and Alex Waibel, Fast Bootstrapping of LVCSR Systems with Multilingual Phoneme Sets. Proceedings of the 5^th European Conference on Speech Communication and Technology (Eurospeech-1997), Vol. 1 pp 371--373, Rhodes, Greece, September 1997.

1997 Tanja Schultz, Detlef Koll, and Alex Waibel, Japanese LVCSR on the Spontaneous Scheduling Task with JANUS-3. Proceedings of the 5^th European Conference on Speech Communication and Technology (Eurospeech-1997), Vol. 1 pp 367--370, Rhodes, Greece, September 1997.

1997 Tanja Schultz, Martin Westphal, and Alex Waibel, The GlobalPhone Project: Multilingual LVCSR with JANUS-3. Multilingual Information Retrieval Dialogs: 2nd SQEL Workshop, pp 20--27, Plzeň, Czech Republic, April 1997.

1996 Tanja Schultz und Hagen Soltau, Automatische Identifizierung spontan gesprochener Sprachen mit neuronalen Netzen. Proceedings of the 3^rd Conference on Natural Language Processing and Speech Technology (KONVENS-1996), pp 102--110, Bielefeld, Germany, October 1996.

1996 Tanja Schultz, Ivica Rogina, and Alex Waibel, LVCSR-based Language Identification. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-1996), pp 781--784, Atlanta, GA, May 1996.

1995 Bernhard Suhm, Petra Geutner, Thomas Kemp, Alon Lavie, Laura Mayfield, Arthur McNair, Ivica Rogina, Tanja Schultz, Tilo Sloboda, Wayne Ward, Monika Woszczyna, and Alex Waibel, JANUS: Towards Multilingual Spoken Language Translation. ARPA Workshop on Speech and Natural Language Technology (SLT-1995), pp 185-189, Austin, Texas, September 1995.

1995 Tanja Schultz, Ivica Rogina, and Alex Waibel, Experiments with LVCSR based Language Identification. Proceedings of the Speech Research Symposium SRS XV, pp 89--94, Baltimore, MD, June 1995.

1995 Tanja Schultz and Ivica Rogina, Acoustic and Language Modeling of Human and Nonhuman Noises for Human-to-Human Spontaneous Speech Recognition. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-1995), Vol. 1 pp 293--296. Detroit, MI, May 1995.

1995 Petra Geutner, Bernhard Suhm, Finn-Dag Buø, Thomas Kemp, Laura Mayfield, Arthur McNair, Ivica Rogina, Tanja Schultz, Tilo Sloboda, Wayne Ward, Monika Woszczyna, and Alex Waibel, Integrating Different Learning Approaches into a Multilingual Spoken Language Translation System, Connectionist, statistical and symbolic approaches to learning for natural language processing, Lecture Notes in Artificial Intelligence, pp 117-131. Springer, Berlin, Heidelberg, March 1995.

1994 Monika Woszczyna, Naomi Aoki-Waibel, Finn-Dag Buø, Noah Coccaro, Keiko Horiguchi, Thomas Kemp, Alon Lavie, Arthur McNair, Thomas Polzin, Ivica Rogina, Carolyn Rose, Tanja Schultz, Bernhard Suhm, Masaru Tomita, and Alex Waibel, JANUS 93: Towards Spontaneous Speech Translation. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-1994), Vol. 1 pp 345--348. Adelaide, Australia, May 1994.

Technical Reports and Distributed Papers:

1995 Tanja Schultz, Identifizierung von Sprachen -Exemplarisch aufgezeigt am Beispiel der Sprachen Deutsch, Englisch und Spanisch. Diploma thesis, Institut für Logik, Komplexität und Deduktionssysteme, Universität Karlsruhe, April 1995.

1994 Tanja Schultz, Akustische Modellierung sprachlicher und nichtsprachlicher Geräusche. Studienarbeit, Institut für Logik, Komplexität und Deduktionssysteme, Universität Karlsruhe, Juni 1994.

Evidence of External Reputation

Invited Panels:

2001 Tanja Schultz, Portability of Automatic Speech Recognition Technology to new Languages: Multilinguality Issues and Speech/Text Resources. Automatic Speech Recognition and Understanding (ASRU-2001), Madonna di Campiglio, Italy, December 2001.

Inivited Talks:

2001 Tanja Schultz, Language Independent and Adaptive Speech Recognition. Speech Seminar at Johns Hopkins University, November 2001.

1999 Tanja Schultz, Multilinguale Spracherkennung. Verbmobil Phase 2, 10. Projektlenkungssitzung, Munich, Germany, December 1999.

1999 Tanja Schultz, Multilinguale Spracherkennung. Verbmobil Phase 2, 9. Projektlenkungssitzung, Stuttgart, Germany, May 1999.

1998 Tanja Schultz, Spracherkennung und Sprachenidentifizierung. Verbmobil Phase 2, 7. Projektlenkungssitzung, Bonn, Germany, May 1998.

1997 Tanja Schultz, Verbmobil-II Data collection. ATR, Kyoto, Japan, September 1997.

1997 Tanja Schultz, Japanese LVCSR on SST with Janus-3. University of Electro-Communication (UEC), Tokyo, Japan, September 1997.

1996 Tanja Schultz, Janus-3 Speech Recognition Toolkit. ATR, Kyoto, Japan, July 1996.

1996 Tanja Schultz, Recognition Engine for the Japanese Spontaneous Scheduling Task. University of Electro-Communication (UEC), Tokyo, Japan, July 1996.

Coordinating and Visiting Positions:

1999-2000 Module-Coordinator in Verbmobil for Speech Recognition

1997 (May) Visiting Researcher

Carnegie Mellon University, Interactive Systems Labs

1996 (July) Visiting Researcher

Advanced Telecommunication Research (ATR)

External Professional Activities

Professional Affiliations:

IEEE member

German Society of Computer Science (GI)

European Language Resources Association (ELRA)

Program Committees:

HLT-2001

Journal Reviews:

Speech Communication Journal

IEEE Transactions on Speech and Audio Processing

List of Courses Taught

Instructor:

• Speech Recognition and Understanding (11-751), Language Technologies Institute, CMU, Fall 2001
• Advanced Speech Lab (11-753), Language Technologies Institute, CMU, Spring 2001

Lectures, Labs:

• Speech Recognition and Understanding (11-751), Language Technologies Institute, CMU, Fall 2000
• Hands-on Lab on Speech Recognition, University of Karlsruhe, 1998 and 1999

Student Advising

Ph.D. Committees:

In Progress Hua Yu (Committee Member). Recognizing Conversational Speech in Meetings, Language Technologies Institute, Carnegie Mellon University.

2001 Laura June Mayfield-Tomokiyo (Committee Member). Recognizing non-native speech: Characterizing and adapting to non-native usage in speech recognition, Language Technologies Institute, Carnegie Mellon University.

LTI Ph.D. Students Co-advised:

Since 2001 Kornel Laskowski

Since 2001 Szu-Chen (Stan) Jou

Since 2000 Zhirong Wang

Since 2000 Qin Jin

LTI Master’s Students Co-advised:

2000-2001 Szu-Chen (Stan) Jou

2000-2001 Kornel Laskowski

Karlsruhe Master’s Students Co-advised (Master’s thesis):

2001 Jamal Abu-Alwan. Arabic Speech Recognition, Institut für Nachrichtentechnik, Fakultät für Elektotechnik und Informationstechnik, Universität Karlsruhe.

2000 Stefan Raschke. Multilingual Speech Recognition by Combining Monolingual Engines. Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1999 Daniel Kiecza. Data-driven determination of appropriate dictionary units for Korean LVCSR, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe.

1998 Jürgen Reichert. Chinese Speech Recognition, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1998 Kenan Çarkı. Turkish Large Vocabulary Speech Recognition, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1997 Hagen Soltau. Recognition of Music Types, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

Karlsruhe Master’s Students Co-advised (Independent study thesis):

1999 Roald Wolff. Adaptation of Polyphone Decision Trees to new Languages, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1998 Stefan Raschke. Automatic Generation of a Pronunciation Lexicon and Bootstrapping of a Serbo-Croatian Speech Recognizer, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1998 Olfa Karboul-Zouari. About the Standard Arabic Language and Romanization of its Script, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1998 Jürgen Reichert. Pinyinzation and Segmentation of Mandarin Chinese, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

1996 Hagen Soltau. Language Identification with Neural Networks, Institut für Logik, Komplexität und Deduktionssystems, Fakultät für Informatik, Universität Karlsruhe. (Thesis in German)

Service and Committee Work