首页> 外文会议>International Conference on speech and computer >Semi-Supervised Training of DNN-Based Acoustic Model for ATC Speech Recognition
【24h】

Semi-Supervised Training of DNN-Based Acoustic Model for ATC Speech Recognition

机译:基于DNN的ATC语音识别声学模型的半监督训练

获取原文

摘要

In this paper, we describe a semi-supervised training method used to generalize the Air Traffic Control (ATC) speech recognizer. The paper introduces the problems and challenges in ATC English recognition, describes available datasets and ongoing research projects. The baseline recognition model is then used to recognize the unlabelled data from a publicly available source. We used the LiveATC community portal which records and archives the recordings of ATC communication near the airports. The recognized unlabelled data are filtered using the data selection procedure based on confidence scores and the recognition acoustic model is retrained to obtain a more general model. The results on accented Czech and French data are reported.
机译:在本文中,我们描述了一种用于推广空中交通管制(ATC)语音识别器的半监督训练方法。本文介绍了ATC英语识别中的问题和挑战,描述了可用的数据集和正在进行的研究项目。然后,使用基线识别模型来识别来自公开来源的未标记数据。我们使用LiveATC社区门户网站来记录和存档机场附近的ATC通信记录。使用基于置信度得分的数据选择过程对识别出的未标记数据进行过滤,并对识别声学模型进行重新训练以获得更通用的模型。报告了重读的捷克和法国数据的结果。

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