Scenarios for embracing errorful automatic speech recognition

Abstract

Errorful speech recognition can be embraced in the design of automatic speech recognition (ASR) support for the Magistrates Court. In this paper we describe processes and scenarios that led to a design by examining work practices and considering a more realistic understanding of ASR technology than is promoted in ASR literature.This paper also uses scenarios in a novel way to package and communicate field work data in a way that is accessible to a wide range of stakeholders.