Policy Indications: India’s Impending Growth in Education and Skills Market: A Report  |  Technology Inceptions: Strong Soft Materials are on the Move!  |  Rajagiri Round Table: Learning Through Games-Art and Science of Serious Games  |  Science Innovations: How Nucleoli Exist as Stable Droplets within the Nucleus?  |  Career News: Indian School of Business Inviting application for Aspiring Entrepreneurs  |  Health Monitor: Early Diagnosis and Treatment of Autism Spectrum Disorder Effective  |  Health Monitor: “School Meal Coalition” an Initiative by the UN  |  Policy Indications: WHO’s #HealthyAtHome Challenge for Students  |  Science Innovations: Another Planet Discovery!  |  Higher Studies: Hebrew University of Jerusalem's International Med-Tech Innovation MBA  |  Higher Studies: University of Birmingham Dubai invites applications for M.Sc. Urban Planning  |  Leadership Instincts: UNICEF’s comprehensive statistical analysis finds that nearly 240 million childr  |  Technology Inceptions: Quantum Dots can be Improvised in Tracking Biochemical Pathways of a Drug  |  Technology Inceptions: MIT promotes ‘Back to Bicycles’ with Artificial Intelligence  |  Policy Indications: Cambridge’s New Curriculum matches NEP 2020  |  
November 05, 2021 Friday 11:51:20 AM IST

Automatic speech recognition developed by MIT

Researchers at MIT and elsewhere have tackled the problem of automated speech-recognition technology that don’t exist for less common languages by developing a simple technique that reduces the complexity of an advanced speech-learning model, enabling it to run more efficiently and achieve higher performance. The technique developed by the researchers of MIT involves removing unnecessary parts of a common, but complex, speech recognition model and then making minor adjustments so it can recognize a specific language. Because only small modifications are required once the larger model is cut down to size, it is much less expensive and time-consuming to teach this model an uncommon language. 

This work would be a help in the playing field of bringing automatic speech-recognition systems to many areas of the world where they have yet to be deployed. The systems are important in some academic environments, where they can assist students who are blind or have low vision, and are also being used to improve efficiency in health care settings through medical transcription and in the legal field through court reporting. Automatic speech-recognition can also help users learn new languages and improve their pronunciation skills. This technology could even be used to transcribe and document rare languages that are in danger of vanishing.  

Comments