Automatic Speech Recognition Survey

Voice Search Voice Recognition by Mohamed Hassan from Pixabay

Abstract

Automatic Speech Recognition (ASR) is a process of transcribing speech similar to the job of human transcribers. ASR is a multi-purpose technology and, as such, is a very dense topic. Due to its multitude of utilities, ASR caught the attention of technical experts with a diverse set of backgrounds. Computer scientists, medical specialists, education planners etc., are all actively researching with many simultaneous ongoing projects to improve the usability of multimedia user interfaces. Specifically, the primary motivation behind all these research initiatives is maximizing accessibility for disabled users. This survey delves into moderate detail about some of the incentives in numerous fields.

Publication
For Seneca College - School of Software Design & Data Science
Nicholas Defranco
Nicholas Defranco
Student

Software development student at Seneca College