Singapore to build speech recognition system to speed up emergency response

Emergency responders at the Singapore Civil Defence Force (SCDF) could react more quickly to people in need when a speech recognition system that automatically transcribes information from distress calls becomes reality.

Powered by a speech-to-text engine to be developed at AI Singapore’s new AI (artificial intelligence) Speech Lab, the system – which will transcribe the unique vocabulary used by Singaporeans, including Singapore English, Chinese and dialects – is expected to boost the SCDF’s operational efficiency.

“The SCDF’s 995 operations centre receives close to 200,000 calls for assistance every year,” said Daniel Seet, director of operations and assistant commissioner at the SCDF. “When a call is received, our dispatchers need to ask some questions to determine the nature and severity of the case, to facilitate the deployment of appropriate emergency medical resources.

“In an emergency, every minute counts. The new speech recognition system, if successful, will help reduce the time needed to log in the information. This will improve how the SCDF’s emergency medical resources are dispatched and enhance the overall health outcomes of those in need.”

The SCDF is the first Singapore government agency to work with the AI Speech Lab on the use of artificial intelligence to help frontline officers acquire relevant information while they focus on interacting with people to address their queries or concerns.

“The AI Speech Lab came about as we had, over the last few months, received multiple requests from agencies and companies for a colloquial Singaporean English speech-to-text engine,” said Ho Teck Hua, executive chairman of AI Singapore. “This is a challenge that is unique to Singapore and the region, which is currently not addressed by existing speech engines offered commercially or by major cloud-based AI providers.”

Led by Li Haizhou, an expert in speech, text and natural language processing from the National University of Singapore, and Chng Eng Siong from the Nanyang Technological University, the AI Speech Lab will make use of the world’s first code-switch (mixed-lingual) speech recognition engine developed by the duo.

The novel code-switch speech recognition engine can recognise speech that uses a mix of English and Chinese words in the same sentence, as if they belong to the same language. To adapt to the local context, words such as “hoh boh” (“how are you?” in the Hokkien dialect) are also included in the engine lexicon.

“An automatic speech recognition system that is able to recognise a mix of languages in one conversation is currently not commercially available,” said Li. “This is because training a computer system to recognise different languages is a very complex and challenging task.

“Our recent technological breakthrough is the outcome of several years of research efforts in Singapore. This technology performs better than commercial engines as it can accurately recognise conversations comprising words from different languages and solves a unique Singapore problem.”

AI Singapore, the country’s national AI development programme, is investing S$1.25m to set up the AI Speech Lab. Government agencies and companies are expected to match this investment, bringing the total funding to S$2.5 million over the next three years.