The new release of Voice2Med will enable surgeons and cardiologists to complete medical reports with their voice



August 12, 2021, Moscow — Speech Technology Сenter (part of the Sber ecosystem) has presented a new release of Voice2Med, a product for AI-based completion of medical reports. 

Voice2Med allows the medical documents to be completed in real time by converting the doctor's voice into text. Two new dictionaries of medical terms were added to the existing dictionaries — general practitioner and paediatrician; radiologist of CT, MRI, positron emission tomography (PET); pathologist; doctor of ultrasound diagnostics; and endoscopist. These include the surgeon's dictionary used to complete the patient journal, protocols of operations in the emergency room, and the cardiologist's dictionary used during cardiac examinations. Ensuring a more than 93% accuracy of term recognition required the processing of more than 500 thousand anonymised reports.

Dmitriy Dyrmovskiy, CEO of Speech Technology Center: 'Now, Voice2Med also supports the dictionaries of medical terms for surgeons and cardiologists, which allows details to be recorded by voice, without distracting from the operation or examination, and to devote more time to the patient instead of routine paperwork. Moreover, such out-of-box solutions like Voice2Med.Hospital and Voice2Med.Outpatient Clinic have been developed to simplify the implementation in hospitals and outpatient clinics. In addition to software and training webinars, the workstation includes a professional headset, because a comprehensive solution eliminates the need to spend time on selecting suitable headsets — now everything is available within a single solution.'

Voice2Med has already been successfully used by radiologists, as it operates in 80 medical institutions in Moscow, 35 medical institutions in Mordovia, as well as in Udmurtia, Murmansk, Kemerovo, Volgograd, and is continuing to undergo development. During the examination, the doctor uses a special microphone to dictate information that is decoded and transferred to the report that is open in the medical information system. High-quality speech recognition ensures the completion of medical reports with a minimum number of subsequent corrections. The Centre for Diagnostics and Telemedicine observed a 22% reduction in the time spent on preparing the medical reports in medical institutions of the Moscow Health Department, as it took 5–6 minutes to complete a report before the deployment of voice data entry, and it takes 3–4 minutes to perform the same task after the deployment of the solution.

There are continuous efforts to expand the list of Russian operating systems supporting Voice2Med. Today, these are various versions of Astra Linux and ALT Linux.

Speech Technology Center (part of the Sber ecosystem) is a global developer of products and solutions based on conversational artificial intelligence, machine learning, and computer vision with 30 years of experience. It offers technological expertise in speech technology, as well as facial recognition and voice biometrics. Speech Technology Center Group is focused on creating B2B and B2G AI solutions, with more than 5,000 AI projects completed around the world, including national-scale projects in Mexico, Ecuador, and the Middle East. In Russia, Speech Technology Center solutions are put to use in the largest banks, telecommunications companies, the fuel and energy sector, as well as the public sector. Moreover, they are being used to introduce the Safe&Smart city concept. Speech Technology Center Group’s voice forgery detection and speech recognition technology are on top of the global rankings like NIST, ASVspoof Challenge, VOiCES, and CHiME Challenge.