Researchers at Microsoft have created a speech recognition software that is able to hear language as accurately as humans.
Microsoft issued a research paper on 17th October in which a team of researchers and engineers of the company’s Artificial Intelligence and Research described a speech recognition system that makes the same or fewer errors than humans who professionally transcript files do.
The researchers described a word error rate (WER) of 5.9 per cent. With this accomplishment, the Microsoft company states the computers can now recognize the words in a conversation as well as a person would.
“Even 5 years ago, I wouldn’t have assumed we could have achieved this. I just wouldn’t have assumed it would be possible,” stated Harry Shum, the executive vice president who heads the Microsoft Artificial Intelligence and Research group.
This technology will have broad suggestions for consumer and business products such as Xbox, instant speech-to-text transcription and Cortana among other products.
To achieve these levels of accurateness, researchers employed deep neural networks to store substantial amounts of data — called training sets — that helped systems recognize patterns from human input. Sounds and images were both used to train the network to utilize its stored data more efficiently.
The Microsoft team made use of Microsoft’s Computational Network Toolkit, a homegrown system for deep learning to reach this milestone. The company stated, ‘CNTK’s ability to quickly process deep learning algorithms across various computers running a specialized chip called a graphics processing unit immensely improved the speed at which they were able to do their research and, ultimately, reach human parity.’
The company is now working on ways to make assured that the speech recognition works well in real-life settings that contain additional external factors such as background noise. They will also concentrate on ways to help this technology allot some names to individual speakers when multiple people are talking.