Publications of Bruce Millar


A limited number of my publications are available in portable data format (.pdf) and can be accessed from this page. Others are listed in pdf format and some of these will be made available in time.

[C91]   The Audio-Video Australian English Speech Data Corpus (AVOZES) (with Roland Goecke)
            Proceedings of International Conference on Spoken Language Processing, Jeju, Korea, \
            4-8 October 2004, paper 747

[C90]   Aspects of Speakin Face Data Corpus Design (with Michael Wagner and Roland Goecke)
            Proceedings of International Conference on Spoken Language Processing, Jeju, Korea, \
            4-8 October 2004, p 813
[C86]   Building and maintaining the bridges of spoken language science
            Proceedings of International Conference on Speech Processing, Daejeon, Korea,
            22-24 August 2001, pp 363-372

[C85]   A reassessment of temporal information in speech processing (with D.R.L.Davies)
            Proceedings of Workshop on Innovative Speech Processing, Stratford-on-Avon, England,
            2-3 April 2001, Institute of Acoustics (UK), pp 247-258

[C83]   Prospects for Speech Technology in the Oceania Region
            Proceedings of 8th Australian International Conference on Speech Science and Technology,
            5-7 December 2000, Canberra, pp.434-439
[C74]  Customisation and Quality Assessment of Spoken Language Description
           Proceedings of 5th International Conference on Spoken Language Processing,
           30 November - 4 December 1998, Sydney, Australia, pp.1575-1578
[C72]  A Structure for Comprehensive Spoken Language Description
           Proceedings of 1st International Conference on Language Resources and Evaluation,
           28-30 May 1998, Granada, Spain, pp.1303-1308
[C61]  Text-Independent Speaker Recognition Using VQ, Mixture Gaussian VQ and Ergodic HMMs.
           Proceedings of ESCA Workshop on Automatic Speaker Recognition, Identification and Verification,
           5-7 April 1994, Martigny, Switzerland, pp.55-58
[C57]  Analysis of Type-II Errors for VQ-Distortion Based Speaker Verification.
           Proceedings of ESCA Workshop on Automatic Speaker Recognition, Identification and Verification,
           5-7 April 1994, Martigny, Switzerland, pp.83-86
[C34]  Phoneme classification using neural networks based on acoustic-phonetic structure (with Shuping Ran)
           Proceedings of 2nd European Conference on Speech Communication and Technology, September 1991,
           Vol.1, pp.129-132

A Full Publication Listing is also available on-line.

 Return to Home Page


Last updated: 10 January 2006