|
|
| Fall 2001: CLSP Seminar Series | Tuesday, May 13, 2008 |
With the distribution of speech technology products all over the world, the portability to new target languages becomes a practical concern. As a consequence my research focuses on the question of how to port LVCSR systems in a fast and efficient way.In this talk I describe the approach of estimating acoustic models for new target languages using data from varied source languages but only limited adaptation data from the target language itself. Especially for very time constrained tasks and minority languages it is even reasonable that no training data is available at all. In the talk I illustrate what performance can be expected in these scenarios. The experiments are run in the framework of the GlobalPhone project which investigates LVCSR systems in the 15 languages.
If time permits, I will also show an application of multilingual speech engines to the problems of speaker identification.
Biographical Information
Tanja Schultz received her Ph.D. in Computer Science from University Karlsruhe, Germany in 2000 and is now a Research Associate and member of the faculty at the Language Technologies Institute at the School of Computer Science at Carnegie Mellon University.
Her research activities center around language independent and language adaptive speech recognition but also includes large vocabulary continuous speech recognition systems, human-machine interfaces for conversational and spontaneous speech, as well as language and speaker identification approaches. With a particular area of expertise in multilingual approaches, she spearheads research on portability of speech recognition engines to many different languages.
Tanja Schultz received the FZI award for her outstanding Ph.D. thesis on language independent and language adaptive speech recognition. She is the author of 40 articles published in books, journals, and proceedings. She is a member of the IEEE Computer Society, the European Language Resource Association, and the Society for Computer Science (GI) in Germany.
| The Center for Language and Speech Processing The Johns Hopkins University 3400 North Charles Street, Barton Hall Baltimore, MD 21218 | |||||
 | Telephone: (410) 516-4237 | | Fax: (410) 516-5050 | | E-mail: clsp@clsp.jhu.edu |