首页> 外文期刊>電子情報通信学会技術研究報告. 音声. Speech >Decoding with sub-word network models for out-of-vocabulary words recognition
【24h】

Decoding with sub-word network models for out-of-vocabulary words recognition

机译:利用子词网络模型进行解码,以识别词汇外的词

获取原文
获取原文并翻译 | 示例
获取外文期刊封面目录资料

摘要

This paper proposes a novel decoder, which cope with sub-word models effectively. Sub-word models are devised for recognition of out-of-vocabulary words. Former implementation, which handles sub-word models as registered words, enlarges language model and consumes lots of computational resources. We proposed a structured decoding method, which applies sub-word network models The proposed method makes it possible to search efficiently. Comparing between former implementation and proposed one, the proposed method achieves 90% reduction in language model size, and 50% reduction in CPU time without any deterioration of performance.
机译:本文提出了一种新颖的解码器,可以有效地处理子词模型。设计了子词模型来识别词汇外的词。以前的实现将子词模型作为注册词来处理,扩大了语言模型并消耗了大量计算资源。我们提出了一种结构化的解码方法,该方法应用了子词网络模型。该方法使有效搜索成为可能。与以前的实现和建议的实现相比,该方法实现了语言模型大小减少90%和CPU时间减少50%而性能没有任何下降。

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