Abstract: Pervasive computing has a great potential for many next-generation IT applications. Its “any time, any where, and human-centered” feature makes it a perfect technology for mandarin E-learning application. This paper describes a pervasive computing system design and implementation for mandarin E-learning with many advanced techniques, such as speech and tone recognition, soft switch technique, text to speech technique, voice-mail, etc. The paper proposes a human-centered pervasive computing system model(HPC), a layered architecture analysis and design method(LAAD). Based on the HPC model and the LAAD method, a pervasive computing-based mandarin E-learning system is designed and implemented. The E-learning system can compute the accuracy of speech and tone and supply some used pervasive services.

Key words: pervasive computing, speech recognition, tone recognition, E-learning