Using Automatic Speech Recognition to Improve Reading Comprehension...

点击翻译按钮获取中文摘要

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.