• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>2nd Conference on Speech Technology and Human-Computer Dialogue; Apr 10-11, 2003; Bucharest >EXPERIMENTAL INFORMATION RETRIEVAL SYSTEM BASED ON ROMANIAN CONTINUOUS SPEECH RECOGNITION
【24h】

EXPERIMENTAL INFORMATION RETRIEVAL SYSTEM BASED ON ROMANIAN CONTINUOUS SPEECH RECOGNITION

机译：基于罗马尼亚语连续语音识别的实验信息检索系统

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents practical results concerning the implementation of an experimental information retrieval system based on Continuous Speech Recognition (CSR) in Romanian. The main task of the system is to allow students to access and to retrieve information from a database via an Automatic Speech Recognition (ASR) engine based on Continuous Hidden Markov Models (CHMMs). The system's architecture is composed by a MySQL database with students' information and an ASR engine that transforms the speech commands uttered in continuous manner into a query string for the database. The feedback from the machine is not yet a text to speech one. For experimental purposes the dialog was kept as simple as possible, so a very simple language model was incorporated in order to get the appropriate sequence of commands. This system was our first trial in the application of CSR for a practical purpose aimed to identify inherent problems and to see how language models could be incorporated.
机译：本文介绍了有关罗马尼亚语中基于连续语音识别（CSR）的实验信息检索系统的实施的实际结果。该系统的主要任务是允许学生通过基于连续隐马尔可夫模型（CHMM）的自动语音识别（ASR）引擎访问数据库并从数据库中检索信息。该系统的体系结构由一个具有学生信息的MySQL数据库和一个ASR引擎组成，该引擎将以连续方式发出的语音命令转换为数据库的查询字符串。来自机器的反馈还不是文本到语音的反馈。出于实验目的，对话框尽可能保持简单，因此并入了非常简单的语言模型以获取适当的命令序列。该系统是我们针对企业社会责任的实际应用中的第一个试用版，旨在发现固有问题并了解如何整合语言模型。

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