Print

Rapid Language Adaptation Tools

SPICE

SPICE stands for Speech Processing - Interactive Creation and Evaluation and is a project supported by the National Science Foundation under Grant No. 0415021.

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 6900 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. SPICE 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.

SPICE builds on the existing projects GlobalPhone and FestVox. 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.

 

 

 

Click on SPICE to start the SPICE web-toolkit

 

Read more about SPICE in the following publications:

 

  • SPICE: Web-based Tools for Rapid Language Adaptation in Speech Processing Systems, Tanja Schultz, Alan W Black, Sameer Badaskar, Matthew Hornyak, and John Kominek, Proceedings of Interspeech, Antwerp, Belgium, August 2007. [pdf] 
  • Voice Building from Insufficient Data - Classroom Experience with web-based Development Tools, John Kominek, Tanja Schultz, and Alan W Black, Proceedings of the 6th ISCA Workshop on Speech Synthesis (SSW-6), August 22-24 2007, Bonn, Germany. [pdf]
  • Challenges with Rapid Adaptation of Speech Translation Systems to New Language Pairs, Tanja Schultz and Alan W Black, Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-2006), Toulouse, France, May 15-19, 2006. [pdf]
  •  Rapid Language Portability of Speech Processing Systems, Tanja Schultz, Keynote talk at the ISCA Tutorial and Research Workshop on Multilingual Speech and Language Processing, Stellenbosch, South Africa, April 10, 2006. [pdf]