Embracing errorfulness speech recognition for the ACT Magistrates Court

Kraal, Ben J. (2006) Embracing errorfulness speech recognition for the ACT Magistrates Court. In Gomez, Rafael E. & Gaddum, Nicholas (Eds.) Faculty of Built Environment and Engineering Design Theme Conference 2006, 30 June 2006, Gardens Point Campus, QUT, Brisbane Australia.


This paper is about how (automatic) speech recognition could be used at the ACT Magistrates Court (the Court) in the courtroom. To explore how speech recognition could be used at the Court it was necessary to understand the work process into which a potential speech recognition system would be integrated.

The potential speech recognition system was to aid magistrates at the bench and replace the time-consuming act of writing sentences in long-hand with simply being able to speak them aloud. The magistrates write sentences on a "bench sheet" which is one of many documents in the "defendant's folder". The goal of the speech recognition system was to do away with the handwritten bench sheet.

The first fieldwork that was done was to interview the Chief Magistrate about his work and use of the defendant's folder and observe several magistrates at their work in Court. The Chief Magistrate viewed his work in writing down sentences as "simple". Based on this fieldwork, a proof-of-concept prototype was constructed. A cognitive walk-through of the prototype revealed that it was deficient in a number of areas, particularly in an understanding of the wider work process of the Court. This prompted further fieldwork.

Additional fieldwork was done focussing on the use of the defendant's folder and the bench sheet in by other workers in the court. This fieldwork revealed that the defendant's folder and bench sheet were artefacts that embodied the wider work process of the Court. The defendant's folder also acted to support communication and maintain the work process in space and time through out the court. Further, the bench sheet was an essential part of the work process of the Court and was essential to the work of many people in the court. Even the magistrates, who found writing on the bench sheet time consuming, used their notes on the bench sheet from as an aid to their decisions. Eliminating the bench sheet, as the Chief Magistrate had asked, would have necessitated a complete re-structuring of work on the bench as well as in the "back room" of the Court.

The final part of this paper describes how a speech recognition system was imagined that could fulfil the requirements to remove the handwritten bench sheet while maintaining as much of the existing work process as possible. This was achieved by working with the errorful nature of speech recognition technology rather than seeking to eliminate it.

Impact and interest:

Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

Full-text downloads:

353 since deposited on 10 Jul 2007
14 in the past twelve months

Full-text downloads displays the total number of times this work’s files (e.g., a PDF) have been downloaded from QUT ePrints as well as the number of downloads in the previous 365 days. The count includes downloads for all files if a work has more than one.

ID Code: 8527
Item Type: Conference Paper
Refereed: No
Additional Information: For more information, please refer to the conference's website (see hypertext link) or contact the author.
Author contact details: b.kraal@qut.edu.au
Additional URLs:
Keywords: Embodiment, field work, distributed, errorful, speech recognition
Subjects: Australian and New Zealand Standard Research Classification > INFORMATION AND COMPUTING SCIENCES (080000) > INFORMATION SYSTEMS (080600) > Computer-Human Interaction (080602)
Divisions: Past > QUT Faculties & Divisions > Faculty of Built Environment and Engineering
Copyright Owner: Copyright 2006 The Author
Deposited On: 10 Jul 2007 00:00
Last Modified: 03 Mar 2011 05:42

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page