What is the future of voice recognition?

Voice recognition will bridge the gap between man and machine. Advanced voice technology will soon be ubiquitous and we will be able to do natural conversation with our smart phone. In the very near future, we will have natural spoken conversations with our smart phone.

How accurate are current speech recognition programs?

The current generation of continuous speech recognition systems claims to offer high accuracy (greater than 95 percent) speech recognition at natural speech rates (150 words per minute) on low-cost (under $2000) platforms.

Why is speech recognition difficult for computers?

Speech recognition software isn’t always able to interpret spoken words correctly. This is due to computers not being on par with humans in understanding the contextual relation of words and sentences, causing misinterpretations of what the speaker meant to say or achieve.

Is voice technology the future?

Ultimately, voice technology isn’t a single industry, after all. Rather, it’s a transformative technology that disrupts nearly every industry, like smartphones and the internet did before. The voice and speech recognition market is expected to grow at a 17.2\% compound annualized rate to reach $26.8 billion by 2025.

How accurate is ASR?

Word Error Rate (WER) is a common metric for measuring speech-to-text accuracy of automatic speech recognition (ASR) systems. Microsoft claims to have a word error rate of 5.1\%. Google boasts a WER of 4.9\%. For comparison, human transcriptionists average a word error rate of 4\%.

What is Microsoft’s Speech recognition technology?

Microsoft has made a major breakthrough in speech recognition, creating a technology that recognizes the words in a conversation as well as a person does.

Who are the Microsoft researchers from the speech & dialogue group?

Microsoft researchers from the Speech & Dialogue research group include, from back left, Wayne Xiong, Geoffrey Zweig, Xuedong Huang, Dong Yu, Frank Seide, Mike Seltzer, Jasha Droppo and Andreas Stolcke. (Photo by Dan DeLong)

Can artificial intelligence make speech recognition more accurate?

In a paper published Monday, a team of researchers and engineers in Microsoft Artificial Intelligence and Research reported a speech recognition system that makes the same or fewer errors than professional transcriptionists.

What is the word error rate of speech recognition?

The researchers reported a word error rate (WER) of 5.9 percent, down from the 6.3 percent WER the team reported just last month. The 5.9 percent 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.