【24h】

Transducer optimizations for tight-coupled decoding

机译:用于紧密耦合解码的换能器优化

获取原文
获取原文并翻译 | 示例

摘要

In this paper we apply a framework of finite-state transducers (FST) to uniformly represent various information sources and data-structures used in speech recognition. These source models include context-free language models, phonology models, acoustic model information (Hidden Markov Models), and pronunciation dictionaries. We will describe how this unified representation can serve as a single input model for the recognizer. We will demonstrate how the application of various levels of optimizations can lead to a more compact representation of these transducers and evaluate the effects on recognition performance, in terms of accuracy and computational complexity.
机译:在本文中,我们应用有限状态换能器(FST)的框架来统一表示语音识别中使用的各种信息源和数据结构。这些源模型包括无上下文语言模型,语音模型,声学模型信息(隐马尔可夫模型)和发音词典。我们将描述该统一表示如何作为识别器的单个输入模型。我们将演示各种优化级别的应用如何导致这些换能器的更紧凑表示,并就准确性和计算复杂性评估评估识别性能的影响。

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