Audio multimedia conferencing system based on the technology of speech recognition

摘要

In this paper, the technology of speech recognition (SR) is introduced into the audio multimedia conference system (PACS) which is operated on a LAN. With the help of SR, the speech of any attendant is identified and translated from audio signal into text signal that can be saved and edited later. Based on the construction of this system, three logical modules are described: manage-node part, record-none part and conference communication-node part. Experimental results show that the performance of this system is satisfactory.