next up previous contents
Next: Task 6.3: Status Up: Task 6.3: Algorithms Porting Previous: Task 6.3: Algorithms Porting

Task 6.3: Task Objective

The baseline ( WERNICKE) recognizer runs on standard Unix workstations (including SUN, HP, SGI and PC/Linux). However, the training systems require specialized high-performance hardware. In WERNICKE training was performed using the RAP hardware and software platform. The use of Torrent-based systems in SPRACH will require applications code (particularly neural network training software) to be ported from the RAP to Torrent. Although this porting effort will be reduced by the similarity of the new matrix-vector calls to the older RAP libraries, an additional effort will be required by the partners to fully exploit the architecture of SPERT and the SPRACHSTATION. This task will also cover any coding effort necessary to implement new algorithms on this hardware. The recurrent neural network training software developed as part of the WERNICKE project runs on RAP hardware. The objective was to port this code to Torrent so that network training could be performed using SPERT.

Christophe Ris