Using Automatic Speech Recognition to Improve Reading Comprehension...

阅读理解能力不足已成为一个严峻的民族问题；职场文盲在企业再培训、工业事故和竞争力下降上花费了数十亿美元。尽管智能辅导系统可以提供帮助，但它们无法看到或听到学生，限制了它们在诊断和纠正理解缺陷方面的有效性。这个试点项目将通过使用一种新的跨学科方法来测试解决这一基本限制的可行性，这种方法是由高速计算、自动语音处理、阅读研究和人工智能的最新进展所实现的。它将监测儿童对基础科学材料的口语阅读，使用自动识别语音和韵律特征（如犹豫和语调）来提取教师和阅读专家认为在教学上有用的信息。成功将为在交互式教学软件中利用这些信息的后续工作奠定基础。这项工作的意义在于在学生和计算机之间开辟了一个基于双向语音通信的强大的新渠道，使理解至关重要的技术领域的创新教学应用成为可能。受影响的人群包括数以百万计的1-3年级的儿童，在这个阶段，口语阅读是最重要的。但是，这个结果应该适用于产业培训、成人文盲、英语作为第二语言和外语学习。

Deficiency in reading comprehension has become a critical national problem; workplace illiteracy costs billions of dollars in corporate retraining, industrial accidents, and reduced competitiveness. Although intelligent tutoring systems could help, their inability to see or hear students limits their effectiveness in diagnosing and remediating deficits in comprehension. This pilot project will test the feasibility of addressing this fundamental limitation by using a novel interdisciplinary approach made possible by recent advances in high-speed computing, automated speech processing, reading research, and artificial intelligence. It will monitor children's oral reading of elementary science material, using automated recognition of connected speech and prosodic features (such as hesitation and intonation) to extract information identified by teachers and reading experts as pedagogically useful. Success will lay the foundation for follow-on work to exploit this information in interactive instructional software. The significance of this work includes opening a powerful new channel between student and computer based on two-way speech communication, enabling innovative tutorial applications in technical areas where comprehension is vital. Those affected include millions of children in grades 1-3, where oral reading is most important. However, the results should apply to industrial training, adult illiteracy, English as a second language, and foreign language study.