0


言语中的意向性:对计算模型的启示

Intentionality in Speech: Implications for Computational Models
课程网址: http://videolectures.net/interACT2016_moore_computational_models/  
主讲教师: Roger K. Moore
开课单位: 旗舰企业
开课时间: 2016-07-31
课程语种: 英语
中文简介:
口语处理领域通常将语音视为经典的刺激-反应行为,因此人们对使用最新的机器学习技术(如深度神经网络)来估计假定的非线性变换非常感兴趣。然而,在现实中,演讲并不是一个静态的过程,而是一个复杂的联合行为,它是由演讲者、听者和他们各自的环境环境之间积极管理的动态耦合产生的。多层次的反馈控制在维持必要的交流稳定性方面起着至关重要的作用,这意味着在当代SLP方法中存在着被忽视的重要依赖性。本次演讲将在更广泛的意向行为背景下讨论这些问题,并将深入了解计算模型的含义。
课程简介: The field of spoken language processing typically treats speech as classic stimulus-response behaviour, hence there is strong interest in using the latest machine learning techniques (such as Deep Neural Networks) to estimate the assumed non-linear transforms. However, in reality, speech is not a static process - rather it is a sophisticated joint behaviour resulting from actively managed dynamic coupling between speakers, listeners and their respective environmental contexts. Multiple layers of feedback control play a crucial role in maintaining the necessary communicative stability, and this means that there are significant dependencies that are overlooked in contemporary SLP approaches. This talk will address these issues in the wider context of intentional behaviour, and will give an insight into the implications for computational models.
关 键 词: 口语处理领域; 机器学习技术; 动态耦合
课程来源: 视频讲座网
数据采集: 2021-12-03:zkj
最后编审: 2021-12-03:zkj
阅读次数: 38