A STADY ON THE UNIVERSAL ASSISTIVE TECHNOLOGY DEVICES TO DEVELOP COMMUNICABILITY OF THE PEOPLE WITH MENTAL RETARDETION, AUTISTIC DISORDER AND OTHER DISABILITIES

我们调查了为精神发育迟滞和自闭症患者开发的交流装置“图片助手”的有效性。另一方面，我们建立了一个发音障碍者的声学模型，并利用ECU对家庭信息家电操作任务中的语音识别进行了评估。此外，我们还研究了手足徐动症脑瘫患者的多模式语音识别。由于与语音相关的肌肉的紧张，语音的清晰度往往会变得不稳定，从而导致语音识别的退化。因此，我们使用多声学框架作为声学特征来解决这一问题。除了声学特征外，视觉特征还用于提高真实环境中的噪声稳健性。然而，由于脑瘫患者有不规律地移动头部的倾向，导致了认知问题。因此，我们研究了一种基于主动外观模型的姿态稳健的视听语音识别方法来解决这个问题。

We investigated the effectiveness of the communication device "Picture aid" developed for the people with mental retardation and autistic disorder. On the other hand, we built an acoustic model for a person with articulation disorder and evaluated speech recognition in the task of operation for home information appliances by ECU. Further we investigated the multimodal speech recognition of them resulting from athetoid cerebral palsy. The articulation of speech tends to become unstable due to strain on speech-related muscles, and that causes degradation of speech recognition. Therefore, we use multiple acoustic frames as an acoustic feature to solve this problem. In addition to acoustic features, visual features are used to increase noise robustness in a real environment. However, there are recognition problems resulting from the tendency of those suffering from cerebral palsy to move their head erratically. So, we investigated a pose-robust audio-visual speech recognition method using an Active Appearance Model to solve this problem.