Dictate IT Live taps deep learning for ‘next-generation’ clinical speech recognition

  • 22 May 2018
Dictate IT Live taps deep learning for ‘next-generation’ clinical speech recognition

Clinical speech services and software specialist Dictate IT has launched a real-time automatic speech recognition engine for medical professionals. 

The new Dictate IT Live tool uses a combination of deep learning and neural networks to convert speech into text without the need to first train a voice profile.

It has been made available to all registered primary care practitioners in the UK on a free trial basis starting today (22 May).

Dictate IT Live  has been designed to help GPs save time and money by removing the need for them to outsource dictations to third-party transcription services.

The system comprises a smartphone and desktop app running in unison. Upon launching the applications, speaking into a smartphone will generate text within the window of the desktop client.

The completed transcription can then be entered into the GP’s clinical workflow or word processing application for use in medical documents, such as referral letters.

James Fone, Dictate IT product manager, explained that unlike most speech recognition platforms, Dictate IT Live worked “straight out of the box”, without first having to train it against an individual voice profile.

As a result, the system offers a much better “standing start” than competitor products, Fone said.

While speech recognition platforms frequently use repackaged APIs offered by US firms like Microsoft and Nuance, Dictate IT Live uses a ‘next-generation’ engine that has been developed entirely in-house by the British firm.

Further, it has been developed specifically for UK medical requirements.

Mark Miller, CEO of Dictate IT, told Digital Health News: “People have been talking about live speech recognition in primary care for such a long time, and to be honest it’s never really caught on.

“There are really no British companies that have any capability in this sector at all, and therefore none of the technologies that have been developed have been specific to British problems.”

Clinical software, consumer appeal

The cloud-based Dictate IT Live platform is hosted at Amazon Web Services’ London data centre.

Data transmitted via the app is secured using AES 256 encryption, with no information stored on the user’s mobile device.

All UK GPs are eligible to a two-month, no-commitment unlimited use trial.

While GPs are the primary audience, Fone suggested that Dictate IT Live could have further appeal within clinical circles.

“The idea is to try to make this like a consumer product that they want to try out,” he said.

Epsom Medical Centre has been running live trials of Dictate IT Live for the past six months.

Customer services manager, Ian Williams, suggested feedback from clinicians had been positive.

“The standard dictation packages out there learn by you making the changes yourself, whereas this actually works straight out of the box,” said Williams.

“The clinician is able to dictate, quickly tidy and dispatch to the GP so that the referral letter can be with the GP by the time the patient is driving home.”

GPs interested in Dictate IT Live can register for a free trial at https://dictateitlive.co.uk/

Subscribe to our newsletter

Subscribe To Our Newsletter

Subscribe To Our Newsletter

Sign up

Related News

AI platform for arthritis detection secures £1.2m grant

AI platform for arthritis detection secures £1.2m grant

Henley Business School has been awarded an £1.2m grant to develop an AI system for early detection of rheumatic and musculoskeletal diseases. 
Leeds Teaching Hospitals trials AI prostate cancer diagnosis tool

Leeds Teaching Hospitals trials AI prostate cancer diagnosis tool

Leeds Teaching Hospitals NHS Trust (LTHT) is piloting an AI tool to assess whether it can improve prostate cancer diagnosis.
MHRA issues transparency guidance for machine learning medical devices

MHRA issues transparency guidance for machine learning medical devices

The Medicines and Healthcare products Regulatory Agency (MHRA) has published guidance on transparency for machine learning medical devices.