London: Scientists are on track to develop a new software which they claim would make conversing with a computer rather more productive.
According to the `New Scientist`, an international team is working on an already developed technology known as automatic speech recognition (ASR) which converts the spoken word to text.
"State-of-the-art ASR has an error rate of 30 to 35
per cent, and that`s just very annoying," Simon Tucker at the
University of Sheffield in the UK said.
What`s more, even when ASR gets it right the results
can be unsatisfactory, as simply transcribing what someone
says often makes for awkward reading. People`s speech can be
peppered with repetition, or sentences that just tail off.
"Even if you had perfect transcription of the words,
it`s often the case that you still couldn`t tell what was
going on," sai Alex Pentland, who directs the Human Dynamics
Lab at the Massachusetts Institute of Technology. "People`s
language use is very indirect and idiomatic," he added.
In fact, the team has developed a system called
Catchup, designed to summarise in almost real time what has
been said at a business meeting so the latecomers can well,
catch up with what they missed.