Artificial and online acquired noise dictionaries for noise robust ASR

摘要

Recent research has shown that speech can be sparsely represented using a dictionary of speech segments spanning multiple frames, exemplars, and that such a sparse representation can be recovered using Compressed Sensing techniques. In previous work we proposed a novel method for noise robust automatic speech recognition in which we modelled noisy speech as a sparse linear combination of speech and noise exemplars extracted from the training data. The weights of the speech exemplars were then used to provide noise robust HMM-state likelihoods. In this work we propose to acquire additional noise exemplars during decoding and the use of a noise dictionary which is artificially constructed. Experiments on AURORA-2 show that the artificial noise dictionary works better for noises not seen during training and that acquiring additional exemplars can improve recognition accuracy.