13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Model-based Approaches to Adaptive Training in Reverberant Environments

Yongqiang Wang, Mark J. F. Gales

Engineering Department, Cambridge University, Cambridge, UK

Adaptive training is a powerful approach for building speech recognition systems using non-homogeneous data. This work presents an extension of model-based adaptive training to handle reverberant environments. The recently proposed Reverberant VTS-Joint (RVTSJ) adaptation is used to factor out unwanted additive and reverberant noise variations in multiconditional training data, yielding a canonical model neutral to noise conditions. An maximum likelihood estimation of the canonical model parameters is described. An initialisation scheme that uses the VTS-based adaptive training to initialise the model parameters is also presented. Experiments are conducted on a reverberant simulated AURORA4 task.

Index Terms: reverberant noise robustness, vector Taylor series, adaptive training

Full Paper

Bibliographic reference.  Wang, Yongqiang / Gales, Mark J. F. (2012): "Model-based approaches to adaptive training in reverberant environments", In INTERSPEECH-2012, 1195-1198.