| 阴法明,赵 焱,赵力.连续音素的改进深信度网络的识别算法*[J].,2019,38(1):39-44 |
| 连续音素的改进深信度网络的识别算法* |
| Phoneme recognition based on deep belief network |
| 投稿时间：2018-04-25 修订日期：2018-12-29 |
| 中文摘要: |
| 为提高连续语音识别中的音素识别率，提出一种基于改进并行回火训练的受限波尔兹曼机的音素识别算法。首先，算法利用经过等能量划分后的改进并行回火来训练受限玻尔兹曼机，接着将受限玻尔兹曼机堆叠组成一个深信度网络，从而作为深度神经网络预训练的基础模型，然后通过软最大化层输出，得到用于音素状态后验概率检测的深度神经网络。接着利用少量的标签数据，根据反向传播算法对网络权重进行微调。最后将所得后验概率作为隐马尔科夫的发射概率，然后利用Viterbi解码器实现音素识别。在TIMIT语料库上的实验表明，相比于传统的对比散度类算法提高了约4.5%。在不增加计算量的情况下比原始并行回火算法提高约1%。 |
| 英文摘要: |
| In order to improve the accuracy of phoneme recognition in continuous speech recognition, in this paper, a modified parallel tempering (PT)algorithm applied totrain the Restricted Boltzmann Machine is proposed. Firstly, Restricted Boltzmann Machine(RBM) is trained in light of Metropolis-Hasting for parallel tempering sampling, then stacking up RBMs to form a deep belief network（DBN） as the basis for DNN pre-training ,then by adding an output layer called “softmax” to the network, a deep neural network detecting the posterior probability of phoneme can be created. Subsequently, Backward Propagation algorithm is applied to fine-tune the weights discriminatively with less label data. Finally the sequence of the predicted probability distribution is fed into a standard Viterbi decoder. The experiments show that the proposed method has a better performance on the TIMIT dataset than traditional ways.Its recognition rate is higher 4.5%than CD，and 1% than original PT without more computation. |
| DOI：10.11684/j.issn.1000-310X.2019.01.006 |
| 中文关键词: 并行回火 受限玻尔兹曼机 深信度网络 音素识别 |
| 英文关键词: Parallel tempering Restricted Boltzmann Machine Deep belief network Phoneme recognition |
| 基金项目:国家自然科学基金项目 (61571106) |
|
| 摘要点击次数: 1942 |
| 全文下载次数: 1605 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
