Semiautomatic Improvements of System-Initiative Spoken Dialog Applications Using Interactive Clustering

Overview

While many successful spoken dialog systems have been deployed over telephone networks, the high cost of developing such applications has led to limited adoption. Despite large research efforts in user-initiative and mixed-initiative systems, most commercial applications follow a system initiative approach because they are simpler to design and are found to work adequately. Yet, even designing such system-initiative spoken dialog systems has proven costly when compared with simpler touchtone systems. To address this issue, this paper describes IEEE's efforts in building diagnostics tools to let non-experienced speech developers write usable applications without the need for transcribing calls.