Learn More
Although context-dependent DNN-HMM systems have achieved significant improvements over GMM-HMM systems, there still exists big performance degradation if the acoustic condition of the test data mismatches that of the training data. Hence, adaptation and adaptive training of DNN are of great research interest. Previous works mainly focus on adapting the(More)
Although deep neural networks (DNN) has achieved significant accuracy improvements in speech recognition, it is computationally expensive to deploy large-scale DNN in decoding due to huge number of parameters. Weights truncation and decomposition methods have been proposed to speed up decoding by exploiting the sparseness of DNN. This paper summarizes(More)
Although great progress has been made in automatic speech recognition, significant performance degradation still exists in noisy environments. Recently, very deep convolutional neural networks CNNs have been successfully applied to computer vision and speech recognition tasks. Based on our previous work on very deep CNNs, in this paper this architecture is(More)
Although great progress has been made in automatic speech recognition (ASR), significant performance degradation still exists in distant talking scenarios due to significantly lower signal power. In this paper, a novel adaptation framework, named integrated adaptation with multi-factor joint-learning, is proposed to improve the recognition accuracy for(More)
The tritiated alpha-isobutylhydroxybenzyl alcohol (3H-G018) was found to be able to bind benzodiazepine (BZ) receptor on the rat brain membrane. The 125I labeled G-018 also had the similar binding activity with this receptor. In the present investigation, we observed that gastrodigenin and its derivatives inhibited the 125I-G018 binding of BZ receptor(More)
Smart manufacturing has increasingly become a prominent research topic across the academia and industry during recent years. However, in the real world, most factories' conditions are normally insufficient for implementing full scale smart manufacturing. In order to increase smartness for manufacturing systems under different situations, one may observe(More)
Long Short-Term Memory (LSTM) is a particular type of recurrent neural network (RNN) that can model long term temporal dynamics. Recently it has been shown that LSTM-RNNs can achieve higher recognition accuracy than deep feed-forword neural networks (DNNs) in acoustic modelling. However, speaker adaption for LSTM-RNN based acoustic models has not been well(More)