Unsupervised adaptation for deep neural networks using Alternating Direction Method of Multipliers

In this paper, we continue our work on linear least squares based adaptation (LLS) for deep neural networks. We show that our previously proposed algorithm is a special case of an optimization algorithm called Alternating Direction Method of Multipliers (ADMM). We demonstrate that the adaptation algorithm can improve the performance on various deep neural networks including the bidirectional long short term memory (BLSTM). On the Switchboard subset of the Hub5 2000 evaluation set, we show that LLS adaptation can achieve 6 to 9% relative word error rate (WER) reduction, and improve our two-pass system to 7.5% WER. In this paper, we also analyze the factors that could contribute to the success of an adaptation algorithm. This helps us to understand under what circumstances, adaptation could improve the system performance.