Convolutional deep rectifier neural nets for phone recognition
نویسنده
چکیده
Rectifier neurons differ from standard ones only in that the sigmoid activation function is replaced by the rectifier function, max(0, x). Several recent studies suggest that rectifier units may be more suitable building units for deep nets. For example, we found that with deep rectifier networks one can attain a similar speech recognition performance than that with sigmoid nets, but without the need for the time-consuming pre-training procedure. Here, we extend the previous results by modifying the rectifier network so that it has a convolutional structure. As convolutional networks are inherently deep, rectifier neurons seem to be an ideal choice as their building units. Indeed, on the TIMIT phone recognition task we report a 6% relative error reduction compared to our earlier results, giving an 18.6% error rate on the core test set. Then, with the application of the recently proposed ‘dropout’ training method we reduce the error rate further to 17.8%, which, to our knowledge, is the best result to date on this database.
منابع مشابه
شبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملPhone recognition with hierarchical convolutional deep maxout networks
Deep convolutional neural networks (CNNs) have recently been shown to outperform fully connected deep neural networks (DNNs) both on low-resource and on large-scale speech tasks. Experiments indicate that convolutional networks can attain a 10–15 % relative improvement in the word error rate of large vocabulary recognition tasks over fully connected deep networks. Here, we explore some refineme...
متن کاملConvolutional deep maxout networks for phone recognition
Convolutional neural networks have recently been shown to outperform fully connected deep neural networks on several speech recognition tasks. Their superior performance is due to their convolutional structure that processes several, slightly shifted versions of the input window using the same weights, and then pools the resulting neural activations. This pooling operation makes the network les...
متن کاملEstimation of Hand Skeletal Postures by Using Deep Convolutional Neural Networks
Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...
متن کاملDeep Online Convex Optimization with Gated Games
Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do not apply. This paper provides the first convergence rates for gradient descen...
متن کامل