Ural Federal District now features a virtual voice assistant for patients



Speech Technology Сenter (part of the Sber digital ecosystem) created a voice assistant to optimise the work of the UMMC-Health medical institution in Yekaterinburg. The service reduces the time doctors waste on missed appointments and waiting for the patients, lowers the workload of the call centre staff, cuts the cost of the SMS messaging for the clinic, and fosters customer loyalty.

The robocaller developed by the Speech Technology Сenter calls patients to remind them of upcoming appointments, tells them how to prepare for the procedures, and asks them to confirm their visit. The virtual assistant can either postpone or cancel appointments. It can make over 20,000 calls a month. In the first three weeks alone, the virtual assistant served a quarter of the UMMC-Health's patients, helping them cancel appointments, make new ones, or adjust the date and time of the visit. The service significantly reduced the clinic's financial losses.

The voice assistant was developed jointly by the UMMC-Health clinic, Speech Technology Сenter, and the Sverdlovsk branch of Sberbank.

Dmitriy Dyrmovskiy, Speech Technology Сenter CEO: "The voice was synthesised from scratch, resulting in a uniquely fluent and smooth speech with correct intonation and word stress. We tried to make the tone and the manner of speech as close to normal human speech as possible. The service uses speech recognition technology to understand what the patient is saying. The assistant recognises spontaneous, hardly legible speech, even if the patient is in a noisy environment or interrupts the robot. The Speech Technology Сenter created all technologies and solutions used in the voice robot. With its user-friendly and intuitive interface, the service is reliable and easy to install and use.

Mikhail Sklyar, CEO of UMMC-Health: Our clinic is one of the leading medical institutions in the Ural Federal District. We serve more than 100,000 people each month. The patients used to receive appointment reminders via SMS messages, calls, or push notifications if they had the clinic's mobile app installed. Now, the voice assistant developed by the Speech Technology Сenter reminds them of scheduled appointments, tests, and examinations. In the past three weeks or so, the voice assistant has allowed us to optimise processes and use the clinic's resources more efficiently. About 15% of our patients now cancel their appointments via the voice assistant. This helps us redistribute patient flows by rescheduling appointments for an earlier date and moving the patients up in the queue. The voice assistant reduced some of our financial losses caused by patients not showing up for their appointments.

Vladislav Shilenko, manager of the Sverdlovsk branch of Sberbank:
"The AI-based servicealerts customers according to different user scenarios. Since the voice speech is synthesised and feels completely natural, most users (including older people) cannot distinguish between the robocaller and a human operator. We thank our partners, UMMC-Health, for their positive outlook on innovations and their active digitalisation efforts. We will continue to monitor the usage of the voice assistant and decide whether to expand the list of scenarios that the robocaller uses".

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 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, VOiCES, and CHiME Challenge.