Sequential Maximum Mutual Information Linear Discriminant Analysis for Speech Recognition

Linear discriminant analysis (LDA) is a simple and effective feature transformation technique that aims to improve discriminability by maximizing the ratio of the between-class variance to the within-class variance. However, LDA does not explicitly consider the sequential discrimina-tive criterion which consists in directly reducing the errors of a speech recognizer. This paper proposes a simple extension of LDA that is called sequential LDA (sLDA) based on a sequential discriminative criterion computed from the Gaussian statistics, which are obtained from sequen-tial maximum mutual information (MMI) training. Al- though the objective function of the pro-posed LDA can be regarded as a special case of various discriminative feature trans- formation techniques (for example, f-MPE or the bottom layer of a neural network), the transformation ma-trix can be obtained as the closed-form solution to a generalized eigenvalue problem, in contrast to the gradient-descent-based optimization methods usually used in these techniques. Experi-ments on large vocabulary continuous speech recognition (Corpus of Spontaneous Japanese) and noisy speech recognition task (2nd CHiME challenge) show consistent improvements from stan-dard LDA due to the sequential discriminative training. In addition, the proposed method, despite its simple and fast computation, improved the performance in combination with discriminative feature transformation (f-bMMI), perhaps by providing a good initialization to f-bMMI