arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1301.3605cs.LGcs.CLcs.NEeess.AS
收藏

深度神经网络中的特征学习-语音识别任务研究

Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks

Microsoft Corporation(微软公司);Microsoft Research(微软研究院);Microsoft Research Asia(微软亚洲研究院)

Dong Yu, Michael L. Seltzer, Jinyu Li, Jui-Ting Huang, Frank Seide

摘要:

最近的研究表明,深度神经网络(DNN)在大词汇量语音识别任务中的表现明显优于浅层网络和高斯混合模型(GARCH)。在本文中,我们认为,DNN实现的准确性提高的结果是他们的能力,以提取歧视性的内部表示,是强大的语音信号的许多来源的变化。我们发现,随着网络深度的增加,这些表示对输入中的小扰动变得越来越不敏感,这导致更深的网络具有更好的语音识别性能。我们还表明,DNN不能外推到与训练样本有很大不同的测试样本。然而,如果训练数据具有足够的代表性,则DNN学习的内部特征相对于说话者差异、带宽差异和环境失真是相对稳定的。这使得基于DNN的识别器能够在不需要显式模型自适应或特征归一化的情况下,与基于GARCH或浅层网络的最先进系统一样好或更好地执行。

英文摘要:

Recent studies have shown that deep neural networks (DNNs) perform significantly better than shallow networks and Gaussian mixture models (GMMs) on large vocabulary speech recognition tasks. In this paper, we argue that the improved accuracy achieved by the DNNs is the result of their ability to extract discriminative internal representations that are robust to the many sources of variability in speech signals. We show that these representations become increasingly insensitive to small perturbations in the input with increasing network depth, which leads to better speech recognition performance with deeper networks. We also show that DNNs cannot extrapolate to test samples that are substantially different from the training examples. If the training data are sufficiently representative, however, internal features learned by the DNN are relatively stable with respect to speaker differences, bandwidth differences, and environment distortion. This enables DNN-based recognizers to perform as well or better than state-of-the-art systems based on GMMs or shallow networks without the need for explicit model adaptation or feature normalization.

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。

↑