首页> 外文期刊>Journal of VLSI signal processing systems for signal, image, and video technology >Ensemble Acoustic Modeling for CD-DNN-HMM Using Random Forests of Phonetic Decision Trees
【24h】

Ensemble Acoustic Modeling for CD-DNN-HMM Using Random Forests of Phonetic Decision Trees

机译:使用语音决策树的随机森林对CD-DNN-HMM进行集成声学建模

获取原文
获取原文并翻译 | 示例
           

摘要

We propose a novel approach to generate an ensemble of context-dependent deep neural networks (CD-DNNs) by using random forests of phonetic decision trees (RF-PDTs) and construct an ensemble acoustic model (EAM) accordingly for speech recognition. We present evaluation results on the TIMIT dataset and a telemedicine automatic captioning dataset and demonstrate the superior performance of the proposed RF-PDT+CD-DNN based EAM over the conventional CD-DNN based single acoustic model (SAM) in phone and word recognition accuracies.
机译:我们提出了一种新方法,通过使用语音决策树(RF-PDTs)的随机森林来生成上下文相关的深度神经网络(CD-DNN)的集合,并相应地构建用于语音识别的集合声学模型(EAM)。我们在TIMIT数据集和远程医疗自动字幕数据集上展示评估结果,并展示了基于RF-PDT + CD-DNN的EAM在电话和单词识别精度方面优于基于传统CD-DNN的单一声学模型(SAM)的性能。

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