A system for dynamic 3D visualisation of speech recognition paths

This paper presents an interactive visualisation system that assists users of semi-automatic speech transcription systems to assess alternative recognition results in real time and provide feedback to the speech recognition back-end in an intuitive manner. This prototype uses the OpenGL libraries to implement an animated 3D visual representation of alternative recognition results generated by the Sphinx automatic speech recognition system. It is expected that displaying alternatives dynamically will facilitate early detection of recognition errors and encourage user interaction, which in turn can be used to improve future recognition performance. Categories and Subject Descriptors H.5.1 [Information Interfaces and Presentation]: Multimedia Information Systems; H.5.2 [User Interfaces]: Natural Language General Terms Human Factors Keywords Automatic Speech Transcription, Interactive visualisation, Animated interfaces, Error correction

• Type: Conference
• Year: 2008
• Where: AVI
• Authors: Saturnino Luz, Masood Masoodian, Bill Rogers, Bo Zhang
• Keywords: Automatic Speech Recognition, AVI 2008, Software Engineering, Speech Recognition, Speech Recognition Back-end