Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

ISIS: A Multilingual Spoken Dialog System Developed With CORBA and KQML Agents

Helen Meng (1), Shuk Fong Chan (1), Yee Fong Wong (1), Tien Ying Fung (1), Wai Ching Tsui (1), Tin Hang Lo (1), Cheong Chat Chan (1), Ke Chen (3), Lan Wang (3), Ting Yao Wu (3), Xiaolong Li (3), Tan Lee (2), Wing Nin Choi (2), Yiu Wing Wong (2), P. C. Ching (2), Huisheng Chi (3)

(1) Human-Computer Communications Laboratory, (2) Digital Signal Processing Laboratory, The Chinese University of Hong Kong
(3) National Key Laboratory for Machine Perception, Peking University, Beijing, China

ISIS, which abbreviates Intelligent Speech for Information Systems, is a trilingual spoken dialog system (SDS) for the financial domain. It handles two dialects of Chinese (Cantonese and Putonghua), as well as English the predominant languages in our region. The system supports spoken language queries regarding stock market information and simulated personal portfolios. Real-time information is retrieved directly from a dedicated Reuters satellite feed. ISIS provides a system test-bed for our work in multilingual speech recognition and generation, speaker authentication, language understanding and dialog modeling. Furthermore, ISIS supports our initial explorations in: (i) CORBA's interoperability and scalability for SDS development; in conjunction with (ii) asynchronous humancomputer interaction by delegation to KQML software agents.

Full Paper

Bibliographic reference.  Meng, Helen / Chan, Shuk Fong / Wong, Yee Fong / Fung, Tien Ying / Tsui, Wai Ching / Lo, Tin Hang / Chan, Cheong Chat / Chen, Ke / Wang, Lan / Wu, Ting Yao / Li, Xiaolong / Lee, Tan / Choi, Wing Nin / Wong, Yiu Wing / Ching, P. C. / Chi, Huisheng (2000): "ISIS: A multilingual spoken dialog system developed with CORBA and KQML agents", In ICSLP-2000, vol.2, 150-153.