5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Modelling Inter-Frame Dependence with Preceeding and Succeeding Frames

Philip Hanna, Ji Ming, Peter O'Boyle, F. Jack Smith

School of Electrical Engineering and Computer Science, The Queen's University of Belfast, Northern Ireland, UK

This paper explores the modelling of inter-frame dependence as a means of improving the performance of HMMs. More specifically, a model based on the IFD- HMM (Ming & Smith, 1996) that assumes a dependency upon both succeeding and preceeding frames is proposed. The means by which a dependency upon succeeding frames might be integrated into a HMM framework are explored, and a mathematical outline of the proposed extension given. The results of various tests aimed towards exploring the consequences of introducing succeeding frame dependencies are included. It was found that a dependency upon succeeding frames enabled dynamic spectral information, not found in the preceeding frames, to be usefully employed; resulting in a significant increase in the recognition accuracy. Additionally, it was shown that modelling of the dynamic spectral information (using time-lag sequences) was at least as important as improved modelling of the instantaneous spectra (using multiple mixtures).

Full Paper

Bibliographic reference.  Hanna, Philip / Ming, Ji / O'Boyle, Peter / Smith, F. Jack (1997): "Modelling inter-frame dependence with preceeding and succeeding frames", In EUROSPEECH-1997, 1167-1170.