Using voice servers for speech analytics

Abstract

In speech analytics, voice content is converted to text so that it can be analyzed, impact decisions, improve productivity and provide information accessibility. Transcription adds significant value and improves business processes whenever there is a large amount of recorded voice data. With the rapid growth of telecommunication, broadcast and information technologies, improved audio compression technology and reduced cost of large storage systems, vast amount of voice data is being collected every day. This paper introduces the concept of a Speech Analytics Server, which comprises a transcription gateway extension to standard Voice Servers. The gateway handles the tasks which are specific to transcription services and are not currently handled by basic Voice Servers. In order to enable extensive speech analytics, an interface to an Unstructured Information Management Architecture (UIMA) is implemented. © IEEE.