Analysis of Different Speech Recognition Toolkit for EMR

EasyChair Preprint 6316

Abstract

Healthcare is the most complex and fast moving industry that exists. New technologies are constantly being developed, all with the potential to support the clinical practice by bringing many advantages into the health care sector. Even after these many technological advancement most of the hospitals still resides on traditional paper medical records. Not only it takes up lots of physical space, the interpretation of these medical records is itself a tedious task. Additional to this, odds of losing data is also a major concern. Hence the speech recognition electronic medical record system was introduced. As there are lots of speech to text platforms available the need of better recognition system with better speech parameters is a factor. In order to tackle that this project helps in recognizing better speech to text conversion platforms.

Keyphrases: DeepSpeech, EMR, Google Cloud, IBM Watson, spaCy, speech recognition, text categorization

@booklet{EasyChair:6316,
  author    = {Manu S Mohan and Shan George Mathew and Surya Paul and V.A Nandaraj and Archana Aniyan},
  title     = {Analysis of Different Speech Recognition Toolkit for EMR},
  howpublished = {EasyChair Preprint 6316},
  year      = {EasyChair, 2021}}