 |
ISCA Workshop on Multilingual Speech and Language Processing (MULTILING 2006)Center for Language and Speech Technology, Stellenbosch University, Stellenbosch, South Africa |
 |
|
ISCA Workshop on Multilingual Speech and Language Processing (MULTILING 2006)Center for Language and Speech Technology, Stellenbosch University, Stellenbosch, South Africa |
|
In recent years, speech processing products had been widely distributed all over the world, reflecting a general believe that speech technologies have a huge potential to let everyone participate in today's information revolution and to bridge the language barrier gap. In spite of recent improvements in speech and language technologies, development of speech processing systems still requires significant skills and resources to carry out. With more than 6500 languages in the world, the current cost and effort in building speech support is prohibitive to all but the most economically viable languages.
SPICE (Speech Processing: Interactive Creation and Evaluation) aims to overcome both limitations by providing innovative methods and tools for nonexpert users to develop speech processing models, collect appropriate data to build these models, and evaluate the results allowing iterative improvements. Data and components for new languages will become available to everybody improving the mutual understanding and the educational and cultural exchange across the language boundaries.
In this talk I will give an overview of the approaches developed within the SPICE project to rapidly deploy speech processing systems in new languages. These include methods to create acoustic models and pronunciation dictionaries for speech recognition and synthesis, as well as language models in new languages with only limited or no data available in the language of question. These approaches are evaluated on our multilingual text and speech database GlobalPhone which covers 19 languages.
Bibliographic reference. Schultz, Tanja (2006): "SPICE - an interactive toolkit for rapid portability of speech processing systems to new languages", In MULTILING-2006, paper KN1 (abstract).