• 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 >ON AUTOMATIC SPEECH SYNTHESIS FOR SPOKEN LANGUAGE INTERFACES
【24h】

ON AUTOMATIC SPEECH SYNTHESIS FOR SPOKEN LANGUAGE INTERFACES

机译：语音接口的自动语音合成

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

Spoken language processing is today one of the most appealing domains of science and certainly holds a key position among Information Society technologies. The main reason for this privileged condition is the fact that speech technology can add the simplest and most natural interface to a computing environment, allowing easier information exchange between humans, or between humans and computers. Low-cost friendly and natural speech-enabled interfaces will become a necessity for most of the new practical applications and services demanded by our modern and "mobile" world. Particularly, machine's voice output is already largely required to improve universal access to information, or when the communication through traditional visual display devices becomes difficult or even impossible. This paper describes the present evolution process of spoken language interfaces and evaluates the status in speech synthesis research and implementation, including our work in developing a text-to-speech synthesis system in Romanian. We investigate several strategies that could be used to accelerate progress and show that application-specific design is a possible solution to overcome some of the current obstacles in building efficient speech synthesis systems. Moreover, we argue that simplifications at certain processing levels of these systems are mandatory for many applications, as it is the case for the embedded computing market.
机译：如今，口语处理已成为科学领域中最吸引人的领域之一，并且在信息社会技术中无疑占有重要地位。这种特权条件的主要原因是，语音技术可以向计算环境添加最简单，最自然的界面，从而使人与人之间或人与计算机之间的信息交换更加容易。低成本，友好且自然的语音支持界面将成为现代和“移动”世界所需要的大多数新的实际应用和服务的必要条件。特别地，已经很大地需要机器的语音输出以改善对信息的通用访问，或者当通过传统视觉显示设备的通信变得困难甚至什至不可能时。本文描述了当前语言界面的演变过程，并评估了语音合成研究和实现的状态，包括我们在罗马尼亚开发文本到语音合成系统的工作。我们研究了可用于加快进度的几种策略，并表明针对特定应用的设计是一种可能的解决方案，可以克服在构建有效的语音合成系统中遇到的一些障碍。此外，我们认为，对于许多应用而言，必须在这些系统的某些处理级别进行简化，就像嵌入式计算市场就是这种情况。

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