@inproceedings{90aaff87591b452ab675ff5d619e3fd1,
title = "AusTalk - The Australian speech database: Design framework, recording experience and localisation",
abstract = "Aiming to create a comprehensive Australian speech database, the 'AusTalk' project was carefully designed by 30 speech scientists contributing their disciplinary expertise. Standardised three one-hour audio-visual sessions for each of 1000 speakers around Australia were recorded having diverse components suitable for different research areas. The design of this database provides a good framework for any speech data corpus collection. In this paper, we present the AusTalk design and recording protocol, as well as problems faced and lessons learned. Localisation of this protocol and the potential customisation based on other countries' specifications are discussed. Collecting such speech databases including accent groups is encouraged to boost speech research in areas such as linguistics, speech and speaker recognition, forensic voice comparison, auditory-visual speech processing and many more.",
keywords = "Australian English, Speech corpus, audio-visual data, generalisation",
author = "Sharifa Alghowinem and Michael Wagner and Roland Goecke",
year = "2013",
doi = "10.1109/CITA.2013.6637567",
language = "English",
isbn = "9781479910922",
series = "2013 8th International Conference on Information Technology in Asia - Smart Devices Trend: Technologising Future Lifestyle, Proceedings of CITA 2013",
publisher = "IEEE Computer Society",
booktitle = "2013 8th International Conference on Information Technology in Asia - Smart Devices Trend",
address = "United States",
note = "2013 8th International Conference on Information Technology in Asia, CITA 2013 ; Conference date: 01-07-2013 Through 04-07-2013",
}