• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computer speech and language >Introduction to the Special Issue on The listening talker: context-dependent speech production and perception
【24h】

Introduction to the Special Issue on The listening talker: context-dependent speech production and perception

机译：听力谈话者特刊简介：依赖于上下文的语音产生和感知

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

Speech is efficient and robust, and remains the method of choice for human communication. However, speech is often delivered by machines that are not aware of the context of the listener, potentially reducing the effectiveness of the communication process. The lack of context-awareness is particularly severe in one-way, output-oriented technologies such talking GPS and public address systems. Such machines lack an essential ingredient of face-to-face human interaction: feedback. When people talk, they also listen. When machines talk, they do not listen. As a result, there is no guarantee that the intended message is intelligible, appropriate or well-timed. The current generation of speech output technology is deaf, incapable of adapting to the listener's context, inefficient in use and lacks the naturalness that comes from rapid appreciation of the speaker-listener environment. Insufficient adaptation to the environment also has become a significant problem in human-to-human communications. The ability to communicate from anywhere to anywhere has resulted in a listening environment that is often challenging and rapidly-changing. The far-end party is generally only partly aware of the near-end environment, an issue that is exacerbated by the rapid improvement of noise suppression technology. The far-end party will therefore not adjust her speech to the environment faced by the near-end user.
机译：语音既有效又健壮，并且仍然是人类交流的首选方法。但是，语音通常是由不了解听众上下文的机器传递的，这有可能降低通信过程的效率。在单向，以输出为导向的技术（如会说话的GPS和公共广播系统）中，缺乏上下文感知的情况尤其严重。这样的机器缺乏面对面的人类互动的基本要素：反馈。人们说话时，也会听。当机器讲话时，他们不听。结果，不能保证预期的消息是可理解的，适当的或适时的。当前的语音输出技术是聋的，不能适应听众的环境，使用效率低下，并且缺乏快速欣赏演讲者-听众环境所带来的自然感。对环境的不充分适应也已成为人与人交流中的重要问题。从任何地方到任何地方进行交流的能力导致了一个充满挑战且瞬息万变的聆听环境。远端通常只部分了解近端环境，而噪声抑制技术的快速改进使该问题更加严重。因此，远端方将不会根据近端用户所面对的环境调整其语音。

著录项

  • 来源
    《Computer speech and language》 |2014年第2期|540-542|共3页
  • 作者

    Martin Cooke; Simon King; Bastiaan Kleijn; Yannis Stylianou;

  • 作者单位

    Ikerbasque (Basque Science Foundation), Spain,Language and Speech Laboratory, Facultad de Letras, Universidad del Pais Vasco, Vitoria, Spain;

    Centre for Speech Technology Research, University of Edinburgh, UK;

    Victoria University Wellington, New Zealand;

    Toshiba, Cambridge, UK,Department of Computer Science, University of Crete, Greece;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

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