Voice recognition technology is becoming a cornerstone in modern living, streamlining everything from home automation to professional tasks. Yet, a significant gap persists: speakers of minority languages and those with thick accents or speech disorders, such as stuttering, often find themselves sidelined by these advancements. These individuals face considerable challenges in using speech recognition tools that are meant to control applications, transcribe text, or automate tasks.
Tobi Olatunji, the founder and CEO of Intron Health, is on a mission to bridge this gap. Intron Health is a clinical speech recognition startup boasting Africa’s largest clinical database, with an algorithm trained on 3.5 million audio clips (16,000 hours) from over 18,000 contributors. These contributors, primarily healthcare practitioners, span 29 countries and 288 accents. Olatunji emphasizes that drawing contributors from the healthcare sector ensures medical terms are accurately pronounced and captured, enhancing the utility of the tool in medical contexts.
“Because we’ve already trained on many African accents, it’s very likely that the baseline performance of their access will be much better than any other service they use,” Olatunji notes. Data from Ghana, Uganda, and South Africa is growing, and Intron Health is confident about deploying the model there. This confidence stems from Olatunji’s dual background in healthcare and technology.
Olatunji’s journey in health-tech began with his medical training and practice in Nigeria. During this time, he witnessed firsthand the inefficiencies plaguing the healthcare system, including the overwhelming paperwork and the challenges of tracking it all. He recalls the frustration of repetitive tasks that seemed undeserving of human effort, such as writing patient names on every lab order.
“When I was a doctor in Nigeria, even during medical school, I got irritated easily doing repetitive tasks that did not deserve human effort,” he says. “An easy example is writing a patient’s name on every lab order. It’s frustrating to repeat the patient’s name, age, and date on each form. I always asked, how can we do things better? How can we make life easier for doctors? Can we offload some tasks to another system so doctors can focus on more valuable work?”
These questions propelled Olatunji to the next phase of his life. He moved to the U.S. to pursue a master’s degree in medical informatics from the University of San Francisco, followed by another in computer science at Georgia Tech. His career took shape at various tech companies, including Enlitic, where he built models to automate the extraction of information from radiology text reports, and Amazon Web Services, where he focused on natural language processing for healthcare. These experiences shaped his vision of how U.S.-developed technologies could improve healthcare in Nigeria and other emerging markets.
Intron Health was launched in 2020 with the original aim of digitizing hospital operations in Africa through an Electronic Medical Record (EMR) System. However, the startup faced challenges in adoption as physicians preferred writing over typing. This led Olatunji to explore improving basic data entry for physicians, ultimately leading to the development of Intron Health’s speech recognition technology. The tool, capable of recognizing African accents, has been integrated into existing EMRs and adopted by 30 hospitals across five markets, including Kenya and Nigeria.
The impact of Intron Health’s technology has been immediate and significant. For instance, it has reduced the waiting time for radiology results at one of West Africa’s largest hospitals from 48 hours to 20 minutes. Such efficiencies are critical in healthcare provision, especially in Africa, where the doctor-to-patient ratio remains one of the lowest in the world.
“Hospitals have already spent so much on equipment and technology. Ensuring they apply this tech is important. We’re able to provide value to help them improve the adoption of the EMR system,” Olatunji explains.
Looking ahead, Intron Health is poised for growth, backed by a $1.6 million pre-seed round led by Microtraction, with participation from Plug and Play Ventures, Jaza Rift Ventures, Octopus Ventures, Africa Health Ventures, OpenseedVC, Pi Campus, Alumni Angel, Baker Bridge Capital, and several angel investors. The startup is working to perfect noise cancellation, ensure platform functionality in low bandwidths, enable the transcription of multi-speaker conversations, and integrate text-to-speech capabilities.
The future vision for Intron Health includes adding intelligent systems or decision support tools for tasks such as prescription writing or lab tests. These tools can help reduce doctor errors and ensure adequate patient care while speeding up their work. Intron Health is among the growing number of generative AI startups in the medical space, including Microsoft’s DAX Express, which aim to reduce administrative tasks for clinicians by generating notes within seconds.
The emergence and adoption of these technologies come as the global speech and voice recognition market is projected to be valued at $84.97 billion by 2032, following a compound annual growth rate (CAGR) of 23.7% from 2024, according to Fortune Business Insights.
Beyond building voice technologies, Intron Health is playing a pivotal role in speech research in Africa. The startup has recently partnered with Google Research, the Bill & Melinda Gates Foundation, and Digital Square at PATH to evaluate popular Large Language Models (LLMs) such as OpenAI’s GPT-4, Google’s Gemini, and Anthropic’s Claude across 15 countries. This research aims to identify strengths, weaknesses, and risks of bias or harm in LLMs, ensuring culturally attuned models are available for African clinics and hospitals.
In conclusion, Intron Health’s innovative approach to clinical speech recognition is addressing a critical gap in the healthcare technology landscape. By focusing on the unique challenges of minority languages and thick accents, the startup is not only improving healthcare efficiency but also enhancing accessibility and quality of care across Africa. As voice recognition technology continues to evolve, the work of Intron Health and similar companies will be crucial in ensuring that no one is left behind.
Visit InstaDtataHelp Blogs.
Visit InstaDataHelp News.