[ad_1]
In an effort to support Singapore
emergency phone operators, Singapore Civil Defense Force works with
four other agencies to bring artificial intelligence (AI). This will be done
use a voice recognition system that can transcribe and record each call
received in real time.
Annually, the Singapore Emergency Service
telephone operators send around 200,000 calls. In high stress situations
telephone operators often find themselves inside, every minute is vital.
Thus, in an effort to lighten their workload,
on Singapore Civil
Defense Force (SCDF) and four other government agencies would be
turn to artificial intelligence (AI) to help improve efficiency. This
will be done using a voice recognition system that can transcribe and connect each
call received in real time – even if it's in singlish (Singaporean English).
Currently, the system is programmed to recognize English and Mandarin with
Hokkien and Malay, although it can be customized
incorporate other indigenous dialects.
AI Singapore (ISGF), a
National Research Foundation program invests $ 1.70 million Singapore
to set up the IA Speech Lab, led by the two professors who created the system. the
system has been developed using artificial intelligence, such as in-depth learning
technology, which works on algorithms that mimic the neural of the human brain
Channels to help computers perform new tasks and analyze data.
The director of operations of the SCDF,
Deputy Commissioner Daniel Seet said: "If successful, it will improve
how the SCDF emergency medical resources are distributed and
the health outcomes of those in need. "
He added that the new
The system will reduce the time required for dispatchers in the SCDF operations center to record incoming information.
Shippers
questions from the caller to determine the nature and severity of the case, to make sure
the appropriate emergency medical resources are sent
The AI Speech Lab is directed
by Professor Li Haizhou, expert in speech, text and natural language
treatment of the National University of Singapore, and associate professor
Chng Eng Siong of Nanyang Technological University. Together, both have
had been working on the voice recognition system for almost a decade!
Prof Li said that one
Code switching system, or mixed-lingual, such as this one, is
currently unavailable commercially.
"This technology works better than commercial engines as it can
accurately recognize conversations
including words of different languages. It solves a unique Singaporean problem "
he said.
To develop the system,
the researchers collected over 1000 hours of talking samples from Singapore and
Penang – a state that mixes languages in speech similar to Singapore – as well
as Singaporeans records of radio stations, YouTube and SoundCloud.
These records are
transcribed manually in the text. The system "learns" then
association between the text and the speech samples collected.
The system has "learned" about 40,000 English and Mandarin
words each, and has an accuracy rate of about 90 percent.
Unique words them
system can recognize include "jiak ba bueh"
and "hoh boh" – "do you have
ate "and" how are you "in Hokkien – and local dishes such as
char kway teow and nasi lemak
The laboratory consists of
five AI engineers and located at the Kent Kent Innovation Building 4.0
Ridge Campus.
Professor Ho Teck Hua,
ISGF Executive Chairman, said that the system could also benefit the
can be customized according to their
Mr. Tan Kok Yam, Assistant Secretary of Smart
Nation and Digital Government Agency, said: "The government is eager to
harness artificial intelligence to better serve our citizens. GovTech is
collaborate with AISG to develop solutions that can improve planning and
provision of services. "
Research Director at
research and consulting firm Gartner, M.
Manjunath Bhat, said: "Multilingual voice transcription will do it
easy for seniors and people speaking all dialects to participate in
digital initiatives
"Even
communication systems go from analog
in digital, human language itself remains analog. The new solution allows
computers to speak in the language of the common person as opposed to humans
learn to adapt to digital interfaces. "
Source link
