首页> 外文会议> >Real time neural networks. III. Alternative neural networks for speech applications
【24h】

Real time neural networks. III. Alternative neural networks for speech applications

机译:实时神经网络。三,语音应用的替代神经网络

获取原文
获取外文期刊封面目录资料

摘要

For pt.II, see ibid., p.584-90 (1991). Waibel Sawai and Shikano (1989), have successfully used traditional neural networks (TNNs), in conjunction with a certain time-delay framework, to recognize phonemes in spoken Japanese syllables. In this paper, the authors first describe Waibel et. al.'s time delay neural network model. They then make several modifications to that model and indicate how procedures can be developed to automatically identify key variables and their cross products, within the structured conjunctoid neural net framework rather than the nonparametric TNN framework,.
机译:关于第二点,请参见同上,第584-90页(1991)。 Waibel Sawai和Shikano(1989)成功地使用了传统的神经网络(TNN),并结合了一定的延时框架,以识别日语口音中的音素。在本文中,作者首先描述了Waibel等。等人的时延神经网络模型。然后,他们对该模型进行了几处修改,并指出如何在结构化的结膜神经网络框架而非非参数TNN框架内开发程序以自动识别关键变量及其交叉乘积。

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