A Pipelined Window Implementation of Multilayer Networks with Time-Sequence Input Patterns for Speech Recognition
作者单位：Department of Computer Science City University of Hong Kong KowloonHong Kong
会议名称：《第五届全国人机语音通讯学术会议》
会议日期：1998年
摘 要：正Numerous studies have demonstrated effectiveness of the multilayer networks with time sequences as inputs to the networks. A common design approach used in these neural networks（NN） is incorporation of short delays, of temporal integration, or of recurrent connections. Spectral inputs are applied to input nodes sequentially, one frame at a time, and their corresponding input matrix can be formed. The NNs can thus be integrated into real time speech recognizer because only short delays are used.