Statistical analysis of the relationship between audio and video speech parameters for Australian English

After decades of research, automatic speech processing has become more and more viable in recent years. Audio-video speech recognition has been shown to improve the recognition rate in noise-degraded environments. However, which audio and video speech parameters to choose for an optimal system and how they are related is still an open research issue. Here we present a number of statistical analyses that aim at increasing our understanding of such audio-video relationships. In particular, we look at the canonical correlation analysis and the coinertia analysis which investigate the relationship of linear combinations of parameters. The analyses are performed on Australian English as an example.