A fast learning method for multilayer perceptrons in automatic speech recognition systems
A fast learning method for multilayer perceptrons in automatic speech recognition systems
复制标题
自动语音识别系统中多层感知器的快速学习方法
DOI：
10.1155/2015/797083
复制
发表时间：
2015
影响因子：
1.8
通讯作者：
Su Kaile
中科院分区：
文献类型：
--
作者：
Cai Chenghao;Xu Yanyan;Ke Dengfeng;Su Kaile
我们提出了一种针对大词汇量连续语音识别（LVCSR）任务的多层感知器（MLP）的快速学习方法。基于训练数据分离和余弦函数动态学习率的预调整策略用于提高随机初始 MLP 的准确性。通过基于奇异值分解(SVD)的方法重构预调整的MLP的权重矩阵，降低MLP的维数。使用拟合展开权重矩阵的反向传播（BP）算法来训练重构的MLP，降低了学习过程的时间复杂度。实验结果表明，在LVCSR任务上，与传统的学习方法相比，这种快速学习方法可以实现约2.0倍的加速，并且交叉熵损失和帧精度都有所提高。而且，在交叉熵损失和帧精度损失很小的情况下，它可以实现约3.5倍的加速比。由于该方法比传统方法消耗的时间和空间更少，因此更适合硬件有限制的机器人。
We propose a fast learning method for multilayer perceptrons (MLPs) on large vocabulary continuous speech recognition (LVCSR) tasks. A preadjusting strategy based on separation of training data and dynamic learning-rate with a cosine function is used to increase the accuracy of a stochastic initial MLP. Weight matrices of the preadjusted MLP are restructured by a method based on singular value decomposition (SVD), reducing the dimensionality of the MLP. A back propagation (BP) algorithm that fits the unfolded weight matrices is used to train the restructured MLP, reducing the time complexity of the learning process. Experimental results indicate that on LVCSR tasks, in comparison with the conventional learning method, this fast learning method can achieve a speedup of around 2.0 times with improvement on both the cross entropy loss and the frame accuracy. Moreover, it can achieve a speedup of approximately 3.5 times with only a little loss of the cross entropy loss and the frame accuracy. Since this method consumes less time and space than the conventional method, it is more suitable for robots which have limitations on hardware.