Belongingness of Chinese dialect speech recognition based on deep neural network
-
摘要: 将深层神经网络(Deep Neural Network)应用于汉语方言种属语音识别.基于优化的QuickNet软件,为方言识别实现了一种有监督的DNN逐层预训练方法.在训练时,从3层开始逐层做有监督的神经网络训练,每增长一层的初始权值包含前一层训练好的部分权值和输出端的随机权值.在得到最大层的初始权值后,再进行传统的BP网络训练.该方法和普通神经网络相比识别率有较大提升,可用于移动互联网标准语音识别入口、方言口音鉴识等领域.Abstract: Based on the modified QuickNet software, we proposed a supervised DNN layerwise pre-training method for dialect speech recognition. The pre-training will start from a 3-layer neural network till the maximum layer, during which we will do supervised training. The initial weights of a new layer are composed of the partial trained weights of lower level network and the randomized weights closed to the output layer. Then we will do traditional back-propagation training when the initial weights of the maximum layer network are obtained. This method achieved a relatively higher recognition rate compared with normal neural network training and can be used in mobile speech recognition apps, the recognition of dialects speech and so on.
-
Key words:
- deep neural network /
- dialects speech recognition /
- QuickNet
-
[1] [1] HINTON G, DENG L, YU D, et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups[J]. Signal Processing Magazine, IEEE, 2012, 29(6): 82-97.[2] BAKER J. The DRAGON system-An overview[J]. Acoustics, Speech and Signal Processing, IEEE Transactions on, 1975, 23(1): 24-29.[3] OH K S, JUNG K. GPU implementation of neural networks[J]. Pattern Recognition, 2004, 37(6): 1311-1314.[4] 顾明亮, 沈兆勇. 基于语音配列的汉语方言自动辨识[J]. 中文信息学报, 2006, 20(5): 77-82.[5] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.[6] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.[7] LAROCHELLE H, BENGIO Y, LOURADOUR J, et al. Exploring strategies for training deep neural networks[J]. The Journal of Machine Learning Research, 2009(10): 1-40.[8] BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[J]. Advances in Neural Information Processing Systems, 2007(19): 153.
点击查看大图
计量
- 文章访问数: 1950
- HTML全文浏览量: 22
- PDF下载量: 3328
- 被引次数: 0