Programme uses speech processing and machine learning technology
IIT Bombay. File Pic
The Indian Institute of Technology Bombay (IIT-B) has developed a mobile application that can measure oral reading fluency automatically using speech processing and machine learning technology.
ADVERTISEMENT
The app—Teacher’s Assistant for Reading Assessment (TARA)—will help in examining and enhancing oral reading fluency in students and it has been adopted by the Kendriya Vidyalaya Sangathan (KVS), the institute said on Thursday.
“The system is trained on expert-annotated recordings of children’s reading and currently works for English and Hindi, with its reliability verified to match that of human experts,” said Preeti Rao, a professor from IIT-B’s department of electrical engineering, who led the project, in a statement.
From an audio recording of a child reading a level-appropriate passage aloud, TARA extracts rubrics for ORF (oral reading fluency), including the widely employed WCPM (words correct per minute), said the statement.
Expression is another important dimension of fluent reading that is strongly linked to the reader’s understanding of the text. With TARA, phrasing, intonation and stress in speech are also measured to obtain a holistic score that is indicative of the precise stage of reading development, it added.
The project was funded by the Tata Centre of Technology and Design, the Abdul Kalam Technology Innovation Fellowship as well as from the school education community.
The innovative app has been recently adopted by the KVS for English and Hindi ORF assessment for Std III to VIII involving over seven lakh students in 1,200 schools across India, making it by far the largest such exercise undertaken in the country, it added.
Subscribe today by clicking the link and stay updated with the latest news!" Click here!
