John McKenna is interested in the application of statistical, data-driven, and machine-learning techniques to the processing of speech. More specifically, he is interested in speaker characterisation and voice transformation. He is currently supervising two Ph.D. students ("Machine Learning of Speaker Characteristic Speech Dynamics and Interaction" and "Probabilistic Filtering and Coding of Speech").
He is a member of the NCLT (National Centre for Language Technology) and RINCE (Research Institute for Networks and Communications Engineering), both based at DCU, and is a member of the International Speech Communication Association (ISCA) and the Irish Speech Group (ISG).
He maintains close ties with CSTR (Centre for Speech Technology Research) at the University of Edinburgh, where he completed his PhD studies.
Publications
Errity, A., McKenna, J., and Kirkpatrick, B. (2007), "Dimensionality reduction methods applied to both magnitude and phase derived features," in Proc. of Interspeech 2007 - Eurospeech, Antwerp, Belgium, August 2007(to appear).
Errity, A. and McKenna, J. (2007), "A comparative study of linear and nonlinear dimensionality reduction for speaker identification," in Proc. of the 15th Int. Conf. on Digital Signal Processing (DSP), Cardiff, Wales, July 2007 (to appear).
Errity, A., McKenna, J., and Kirkpatrick, B. (2007), "Manifold learning-based feature transformation for phone classification," in Proc. of the ISCA Tutorial and Research Workshop on Nonlinear Speech Processing (NOLISP), Paris, France.
Errity, A. and McKenna, J. (2006), "An investigation of manifold learning for speech analysis," in Proc. of the Int. Conf. on Spoken Language Processing (Interspeech 2006 - ICSLP), Pittsburgh PA, USA.
Tooher, M. and McKenna, J. (2005), "Application of glottal source information to speech recognition" in Proceedings of SPECOM 2005, Greece.
Errity, A., McKenna, J. and Isard, S. (2004), "Unscented Kalman filtering of line spectral frequencies" in Proc. InterSpeech ICSLP 2004 (Korea).
Tooher, M. and McKenna, J. (2004), "Prediction of the Glottal LF Parameters using Regression Trees" in Proc. InterSpeech ICSLP 2004 (Korea).
McKenna, J.G. (2004), Kalman filtering towards automatic speaker characterisation, Ph.D. Thesis, University of Edinburgh.
Tooher, M. and McKenna, J. (2003), "Variation of glottal LF parameters across F0, vowels and phonetic environment" in Proceedings of ISCA Tutorial and Research Workshop on Voice Quaility Functions, Analysis and Synthesis (VOQUAL '03), Geneva, Switzerland.
McKenna, J.G. (2001), "Automatic glottal closed-phase location and analysis by Kalman filtering", in Proceedings of the 4th ISCA Tutorial and Research Workshop on Speech Synthesis, Pitlochry, Scotland.
McKenna, J. and Isard, S. (1999), "Tailoring Kalman Filtering Towards Speaker Characterisation" in Proc. Eurospeech 99, Budapest, Hungary.