SPEECH RECOGNITION PERFORMANCE ON A NEW VOICEMAIL TRANSCRIPTION TASK

Abstract

In this paper we describe a new testbed for developing speech recognition algorithms - a VoiceMail transcription task, analogous to other tasks such as the Switchboard, CallHome, and the Hub 4 tasks, which are currently used by speech recognition researchers. We describe the collection and use of a new VoiceMail database (that is available to the research community through the LDC), and also describe some algorithmic techniques that were devised based on this data, and the initial results of transcription performance on this task.