In a major breakthrough in the field of speech recognition, researchers have created a technology that recognizes the words in a conversation like people do.
Breast Imaging Reports Generated by Automatic Speech Recognition Have Higher Error Rates
A Canadian study shows that breast imaging reports generated with conventional dictation transcription might be better than those generated using an automatic speech recognition
A Canadian study shows that breast imaging reports generated with conventional dictation transcription might be better than those generated using an automatic speech recognition
‘In a major breakthrough in the field of speech recognition, Microsoft researchers have created a technology that accurately recognizes the words in a conversation like people do.’
The researchers reported a word error rate (WER) of 5.9%, down from the 6.3% WER the team reported in September 2016. The 5.9% error rate is about equal to that of people who were asked to transcribe the same conversation, and it's the lowest ever recorded against the industry standard "Switchboard" speech recognition task.
"We've reached human parity. This is an historic achievement," said Xuedong Huang, the company's chief speech scientist in a Microsoft blog post.
Speech Recognition Pathway in Humans
Research shows that the human brain needs three different processing stages to identify sounds such as speech
Research shows that the human brain needs three different processing stages to identify sounds such as speech
In doing so, the team has beat a goal they set less than a year ago - and greatly exceeded everyone else's expectations as well.
Advertisement
Speech Recognition in Babies Begins Very Early
The ability of infants to recognize speech is initiated as early as nine months.
The ability of infants to recognize speech is initiated as early as nine months.
The research milestone comes after decades of research in speech recognition, beginning in the early 1970s with DARPA, the US agency tasked with making technology breakthroughs in the interest of national security.
Advertisement
Scientists Create New Memory Device to Improve Speech and Image Recognition
Researchers have successfully demonstrated pattern recognition using a magnonic holographic memory device consisting of a magnetic matrix with micro-antennas.
Researchers have successfully demonstrated pattern recognition using a magnonic holographic memory device consisting of a magnetic matrix with micro-antennas.
The milestone will have broad implications for consumer and business products that can be significantly augmented by speech recognition. That includes consumer entertainment devices like the Xbox, accessibility tools such as instant speech-to-text transcription and personal digital assistants such as Cortana.
"This will make Cortana (Microsoft personal assistant) more powerful, making a truly intelligent assistant possible," Shum said.
To reach the human parity milestone, the team used Microsoft's Computational Network Toolkit (CNTK), a home-grown system for deep learning that the research team has made available on GitHub via an open source license.
CNTK's ability to quickly process deep learning algorithms across multiple computers running a specialized chip called a graphics processing unit vastly improved the speed at which the team was able to do research and, ultimately, reach human parity.
Moving forward, the researchers are working on ways to make sure that speech recognition works well in more real life settings.
That includes places where there is a lot of background noise, such as at a party or while driving on the highway.
In the longer term, researchers will focus on ways to 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.
"The next frontier is to move from recognition to understanding," Zweig said.
Source-IANS
