Talking to machines (statistically speaking)
Talking to machines (statistically speaking)
复制标题
与机器对话（从统计学上来说）
DOI：
10.21437/icslp.2002-2
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
S. Young
中科院分区：
文献类型：
--
作者：
S. Young
统计方法长期以来一直是语音识别的主导方法，ASR 中的概率建模现已成为一项成熟的技术。然而，统计方法在口语对话其他领域的使用是最近才出现的，而且还不太成熟。本文从统计建模的角度回顾了口语对话系统。完整的系统首先呈现为部分可观察的马尔可夫决策过程。然后通过引入适当的中间变量来暴露各种子组件。在此框架内审查现有工作的样本，包括对话控制和优化、语义解释、目标检测、自然语言生成和合成。
Statistical methods have long been the dominant approach in speech recognition and probabilistic modelling in ASR is now a mature technology. The use of statistical meth-ods in other areas of spoken dialogue is however more recent and rather less mature. This paper reviews spoken dialogue systems from a statistical modelling perspective. The complete system is first presented as a partially observable Markov decision process. The various sub-components are then exposed by introducing appropriate intermediate variables. Samples of existing work are reviewed within this framework, including dialogue control and optimisation, semantic interpretation, goal detection, natural language generation and synthesis.