Child and adult speaker adaptation during error resolution in a publicly available spoken dialogue system
Child and adult speaker adaptation during error resolution in a publicly available spoken dialogue system
复制标题
在公共口语对话系统中解决错误期间儿童和成人说话者的适应
DOI：
10.21437/eurospeech.2003-259
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
Joakim Gustafson
中科院分区：
文献类型：
--
作者：
L. Bell;Joakim Gustafson
本文介绍了扬声器如何适应他们的语言在错误解决时，互动的动画代理Pixie。在瑞典斯德哥尔摩的电信博物馆收集了一个自发的人机交互语料库。成人和儿童扬声器进行了比较，在错误解决的用户行为和策略。在这项研究中，16名成年人和16名儿童扬声器从语料库中随机选择了近3.000扬声器。然后对该子语料库进行了更详细的分析。结果表明，成人和儿童使用部分不同的策略时，他们的互动与小精灵成为问题。孩子们倾向于逐字重复同样的话语，改变某些语音特征。另一方面，成年人经常修改他们话语的其他方面，如词汇和句法。本研究的结果将有助于构建未来的口语对话系统，改善成人以及儿童的错误处理。
This paper describes how speakers adapt their language during error resolution when interacting with the animated agent Pixie. A corpus of spontaneous human-computer interaction was collected at the Telecommunication museum in Stockholm, Sweden. Adult and children speakers were compared with respect to user behavior and strategies during error resolution. In this study, 16 adults and 16 children speakers were randomly selected from a corpus from almost 3.000 speakers. This sub-corpus was then analyzed in greater detail. Results indicate that adults and children use partly different strategies when their interactions with Pixie become problematic. Children tend to repeat the same utterance verbatim, altering certain phonetic features. Adults, on the other hand, often modify other aspects of their utterances such as lexicon and syntax. Results from the present study will be useful for constructing future spoken dialogue systems with improved error handling for adults as well as children.