基于梯形网络的半监督语言识别方法
A Semisupervised Approach for Language Identification based on Ladder Networks
摘要:
在这项研究中,我们解决的问题,训练神经网络的语言识别使用标记和未标记的语音样本的形式的i向量。我们提出了一个神经网络架构,也可以处理集外语言。我们利用最近提出的梯形网络半监督训练过程的修改版本,优化了去噪自动编码器堆栈的重建成本。我们表明,这种方法可以成功地应用到的情况下,训练数据集是由标记和未标记的声学数据。结果显示,NIST 2015语言识别数据集上的语言识别增强。
英文摘要:
In this study we address the problem of training a neuralnetwork for language identification using both labeled and unlabeled speech samples in the form of i-vectors. We propose a neural network architecture that can also handle out-of-set languages. We utilize a modified version of the recently proposed Ladder Network semisupervised training procedure that optimizes the reconstruction costs of a stack of denoising autoencoders. We show that this approach can be successfully applied to the case where the training dataset is composed of both labeled and unlabeled acoustic data. The results show enhanced language identification on the NIST 2015 language identification dataset.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。