Automated Test of Word Recognition - Phase I

描述（由申请人提供）：在美国，听力学家每年进行超过500万次单词识别测试，相关费用超过1亿美元。这些测试目前由训练有素的听力学家手动进行。本申请描述了使用临床测试记录和自动语音识别系统对受试者的响应进行评分的自动临床语音识别测试的I期开发。还将探讨自动解释考试成绩的方法。其目的是提高该临床测试的准确性和效率，同时大幅降低成本。自动语音识别测试与自动纯音听力图（目前是STI 'R第二阶段项目）相结合，将对大多数听力学患者进行诊断测试，从而为听力学家腾出时间来进行需要他们培训和技能的活动。培训和报销模式的当代变化对自动化临床程序产生了很高的需求。自动化过程可以在现有的听力计上实现，其中个人计算机将控制听力计并运行语音识别软件。

DESCRIPTION (provided by applicant): Over 5 million word recognition tests are administered annually by audiologists in the United States with an associated cost of more then $100 million. These tests are currently performed manually by high-trained audiologists. This application describes a Phase I development of an automated clinical speech recognition test using clinical test recordings and an automated speech recognition system to score the subjects' responses. Methods for automatically interpreting the test scores will also be explored. The objectives are to increase the accuracy and efficiency of this clinical test while substantially reducing the cost. The automated speech recognition test in combination with the automated puretone audiogram (currently an STI'R Phase II project) will perform diagnostic testing of a majority of audiology patients, freeing the audiologists' time for activities that require their training and skill. Contemporary changes in training and reimbursement patterns create a high demand for automated clinical procedures. The automated procedure could be implemented on existing audiometers with a personal computer that would control the audiometer and run the speech recognition software.