首页> 外文OA文献 >Design of a portable microprocessor-based International Phonetic Alphabet (IPA) text-to-speech conversion device for use by the speech impaired
【2h】

Design of a portable microprocessor-based International Phonetic Alphabet (IPA) text-to-speech conversion device for use by the speech impaired

机译:基于便携式微处理器的国际语音字母表(IPA)文本到语音转换设备的设计,供有语音障碍的人使用

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

A portable microprocessor-based alternate communication device was designed and a prototype fabricated. This device allows speech impaired individuals, whose language skills remain intact, to input and edit an utterance of unrestricted vocabulary via a keyboard/LCD display system. The utterance, which is specified using the International Phonetic Alphabet (IPA), is then converted into an appropriate set of speech synthesizer parameters, using context sensitive rules. An interrupt driven system is used to pass each set of parameters, in order and at the appropriate time, to the synthesizer, thus generating an audible output;Tests conducted using the device in its present state have shown the utterance specification process to be slower than desired and the speech produced to be rather robotic in nature. Although understanding the speech generated is sometimes a problem, intelligibility improves with time as the listener becomes used to the synthesized speech and the programmer\u27s ability to specify the utterance improves;As the current implementation does not include rules that vary the suprasegmental features, it is anticipated that the introduction of such rules will improve the quality and intelligibility of the speech output. Further suggestions for future development are provided, and focus on expediting the utterance specification process and improving the quality of the speech generated.
机译:设计了基于便携式微处理器的备用通信设备,并制造了原型。该设备允许语言能力完好无损的语音障碍人士通过键盘/ LCD显示系统输入和编辑不受限制的词汇。然后,使用上下文相关的规则将使用国际语音字母(IPA)指定的语音转换为一组合适的语音合成器参数。中断驱动系统用于按顺序在适当的时候将每组参数传递给合成器,从而产生可听的输出;使用该设备在其当前状态下进行的测试表明,发声规范过程比期望,并且语音产生的本质上是机器人。尽管有时理解生成的语音有时会遇到问题,但随着听众习惯合成语音并提高程序员指定话语的能力,清晰度会随着时间的推移而提高;由于当前的实现不包括改变超细分功能的规则,预计引入这样的规则将改善语音输出的质量和清晰度。提供了进一步的发展建议,重点是加快发声规范过程并提高语音质量。

著录项

  • 作者

    Ishii, Dexter Katsutoshi;

  • 作者单位
  • 年度 1989
  • 总页数
  • 原文格式 PDF
  • 正文语种 en
  • 中图分类

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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