• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >On the use of deep feedforward neural networks for automatic language identification
【24h】

On the use of deep feedforward neural networks for automatic language identification

机译：关于使用深度前馈神经网络进行自动语言识别

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this work, we present a comprehensive study on the use of deep neural networks (DNNs) for automatic language identification (LID). Motivated by the recent success of using DNNs in acoustic modeling for speech recognition, we adapt DNNs to the problem of identifying the language in a given utterance from its short-term acoustic features. We propose two different DNN-based approaches. In the first one, the DNN acts as an end-to-end LID classifier, receiving as input the speech features and providing as output the estimated probabilities of the target languages. In the second approach, the DNN is used to extract bottleneck features that are then used as inputs for a state-of-the-art i-vector system. Experiments are conducted in two different scenarios: the complete NIST Language Recognition Evaluation dataset 2009 (LRE'09) and a subset of the Voice of America (VOA) data from LRE'09, in which all languages have the same amount of training data. Results for both datasets demonstrate that the DNN-based systems significantly outperform a state-of-art i-vector system when dealing with short-duration utterances. Furthermore, the combination of the DNN-based and the classical i-vector system leads to additional performance improvements (up to 45% of relative improvement in both EER and C_(avg) on 3s and 10s conditions, respectively).
机译：在这项工作中，我们对使用深度神经网络（DNN）进行自动语言识别（LID）进行了全面的研究。受到最近在声学模型中使用DNN进行语音识别的成功推动，我们使DNN适应了从短期声学特征以给定发音识别语言的问题。我们提出了两种不同的基于DNN的方法。在第一个中，DNN用作端到端LID分类器，接收语音特征作为输入，并提供目标语言的估计概率作为输出。在第二种方法中，DNN用于提取瓶颈特征，然后将其用作最新i向量系统的输入。实验在两种不同的情况下进行：完整的NIST语言识别评估数据集2009（LRE'09）和来自LRE'09的美国之音（VOA）数据的子集，其中所有语言都具有相同数量的训练数据。这两个数据集的结果都表明，在处理短时语音时，基于DNN的系统明显优于最新的i-vector系统。此外，基于DNN的系统和经典i向量系统的组合还带来了其他性能改进（在3s和10s条件下，EER和C_（avg）相对改进分别达到了45％）。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号