在群体支持系统(Group Support Systems,GSS)的环境下,群体能够在很短时间内产生大量研讨文本,远远超过了人们对信息处理的能力。因此,迫切需要一种能够自动分析和处理群体研讨文本的方法,言语行为分类就是这类方法中有可能实现并且具...在群体支持系统(Group Support Systems,GSS)的环境下,群体能够在很短时间内产生大量研讨文本,远远超过了人们对信息处理的能力。因此,迫切需要一种能够自动分析和处理群体研讨文本的方法,言语行为分类就是这类方法中有可能实现并且具有应用价值的一个。在分析Zeno研讨模型的基础上,提出了适合群体研讨语料的言语行为分类体系。采用基于转换学习的办法,通过引入多阶段转换学习的概念,初步解决了群体研讨文本言语行为分类的问题,并且在议题类别和一些表达主张的类别(如支持和反对)上取得了较好的识别效果。研究群体研讨文本的言语行为分类对于拓展GSS,进而研究和开发自动主持人系统具有重要意义。同时,也为在中文环境下解决其他类型研讨(如网络聊天室、即时聊天工具等)文本的言语行为分类问题提供了参考依据。展开更多
Prosodic structure generation is the key component in improving the intelligibility and naturalness of synthetic speech for a text-to-speech (TTS) system. This paper investigates the problem of automatic segmentation ...Prosodic structure generation is the key component in improving the intelligibility and naturalness of synthetic speech for a text-to-speech (TTS) system. This paper investigates the problem of automatic segmentation of prosodic word and prosodic phrase,which are two fundamental layers in the hierarchical prosodic structure of Mandarin,and presents a two-stage prosodic structure generation strategy. Conditional random fields (CRF) models are built for both prosodic word and prosodic phrase prediction at the front end with diflerent feature selections. Besides,a transformation-based error-driven learning (TBL) modification module is introduced in the back end to amend the initial prediction. Experiment results show that the approach combining CRF and TBL achieves an F-score of 94.66%.展开更多
文摘在群体支持系统(Group Support Systems,GSS)的环境下,群体能够在很短时间内产生大量研讨文本,远远超过了人们对信息处理的能力。因此,迫切需要一种能够自动分析和处理群体研讨文本的方法,言语行为分类就是这类方法中有可能实现并且具有应用价值的一个。在分析Zeno研讨模型的基础上,提出了适合群体研讨语料的言语行为分类体系。采用基于转换学习的办法,通过引入多阶段转换学习的概念,初步解决了群体研讨文本言语行为分类的问题,并且在议题类别和一些表达主张的类别(如支持和反对)上取得了较好的识别效果。研究群体研讨文本的言语行为分类对于拓展GSS,进而研究和开发自动主持人系统具有重要意义。同时,也为在中文环境下解决其他类型研讨(如网络聊天室、即时聊天工具等)文本的言语行为分类问题提供了参考依据。
基金Supported by National Natural Science Foundation of China(90920001)the Key Project of the Ministry of Education of China(108012)Joint-research Project between France Telecom R&DBeijing and Beijing University of Posts and Telecommunications(SEV01100474)
文摘Prosodic structure generation is the key component in improving the intelligibility and naturalness of synthetic speech for a text-to-speech (TTS) system. This paper investigates the problem of automatic segmentation of prosodic word and prosodic phrase,which are two fundamental layers in the hierarchical prosodic structure of Mandarin,and presents a two-stage prosodic structure generation strategy. Conditional random fields (CRF) models are built for both prosodic word and prosodic phrase prediction at the front end with diflerent feature selections. Besides,a transformation-based error-driven learning (TBL) modification module is introduced in the back end to amend the initial prediction. Experiment results show that the approach combining CRF and TBL achieves an F-score of 94.66%.