Improving the performance of an LVCSR system through ensembles of acoustic models

This paper describes our work on applying ensembles of acoustic models to the problem of large vocabulary continuous speech recognition (LVCSR). We propose three algorithms for constructing ensembles. The first two have their roots in bagging algorithms; however, instead of randomly sampling examples our algorithms construct training sets based on the word error rate. The third one is a boosting style algorithm. Different from other boosting methods which demand large resources for computation and storage, our method present a more efficient solution suitable for acoustic model training. We also investigate a method that seeks optimal combination for models. We report experimental results on a large real world corpus collected from the Carnegie Mellon Communicator dialog system. Significant improvements on system performance are observed in that up to 15.56% relative reduction on word error rate is achieved.