A technology that accurately recognizes the words in a conversation
A technology that accurately recognizes the words in a conversation:-With the major breakthrough in the field of speech recognition, Microsoft researchers have recently created a technology that accurately recognizes the words in a conversation like people do — a feat that may could soon help people suffering from the speech-related issues.
The team from the Microsoft Artificial Intelligence and Research has reported a speech recognition system which would make the same or fewer errors than the professional transcriptionists.
The researchers have also reported a word error rate (WER) of 5.9 per cent, down from the 6.3 per cent WER the team reported just the last month.
The 5.9 per cent error rate is about equal to that of people, who were asked to transcribe the same conversation, and it is the lowest ever recorded against the industry standard “Switchboard” speech recognition task.
“We have reached human parity. This is an historic achievement,” said by Xuedong Huang, the company’s chief speech scientist in a Microsoft blog post.
Milestone has been achieved
The milestone means that, for the first time, a computer is capable enough to recognize the words in a conversation as well as a person would.
In doing so, the team has beat a goal they have set less than a year ago — and greatly exceeded everyone else’s expectations as well.
Read Here : Dear Boys, I am Single but not ready to Mingle
The research milestone comes after lot of research in the field of speech recognition, beginning in the early 1970s with DARPA, the U.S. agency has tasked with making technology breakthroughs in the interest of national security.
Moving forward, the researchers are now working on ways to make sure that the speech recognition works well in more real life settings.
It includes places where there is a lot of background noise, such as at a party or also while driving on the highway. In the longer term, researchers will be focusing on ways to further teach computers not just to transcribe the acoustic signals that come out of people’s mouths, but instead to understand the words they are saying.
