Speech Technology Сenter has developed a voice robot that will remind you of your doctor's appointment and inform you on how to prepare for your procedure



Speech Technology Center, a Sber ecosystem company, has created a voice recognition robot that optimizes the work of medical institutions.

This virtual assistant can remind you of your doctor's appointment, saving time from missed appointments for other patients and increasing the throughput of medical institutions, which is especially important today. Additionally, as part of an appointment reminder call, the robot can advise you on how to prepare for or reschedule your appointment. Premiered at the Sber booth during CIPR 2021, this development has the key goals of streamlining doctors’ workload and increasing the availability of medical care in polyclinics. The solution should improve doctors’ efficiency and reduce the number of patients who are unprepared for their procedures.

The technologies and products used to create this voice robot were drawn up in Speech Technology Center’s R&D division: these products employ proprietary NLU technology for speech recognition and synthesis.

Speech synthesis allows the robot to actually "speak". The robot's voice was developed from scratch using synthesis, which made it possible to achieve the virtual assistant's uniquely smooth speech patterns, with correct intonation and semantic accents. We tried to make the timbre and manner of speech as natural and smooth as possible, bringing them as close to the normal human speech as possible. Speech recognition technology is being used to understand what the patient is saying. What makes this technology special is its ability to recognize spontaneous speech that is not always intelligible, like if a patient calls in from a noisy environment or interrupts the robot.

Dmitry Dyrmovsky

CEO, Speech Technology Center

Developed with the support of the National Technology Initiative (NTI), Speech Technology Center's speech recognition technology was recognized as the best in the world during the international competition CHiME 2020.

Speech Technology Center deployed a cloud platform in SberCloud for the operation of standard telephone robots. The portfolio of standard telephone robots includes not only medical cases, but also cases for the energy sector and government agencies. This has increased the adoption speed significantly — launching several cases doesn’t take more than a month now. Speech Technology Center’s omni-channel platform allows you to create robots in the Russian, English, and Spanish languages.

Speech Technology Center is also running a pilot project to introduce a voice robot that collects complaints about a person's well-being before seeing a therapist. During the appointment reminder call (one day before the appointment), the voice assistant will offer the patient a survey on well-being. The firm Doctor Nearby helped develop the robot's AI-driven logic and scenarios. The robotic assistant is currently being tested in five of Moscow's medical and preventive institutions. The key goals are to optimize doctors’ workload and increase the availability of medical care at polyclinics. The solution is supposed to save doctors’ time and allow them to focus on patient examinations and high-quality communication.

 

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.