Microsoft (News - Alert) wants to own more of the voice market and as a result, is focusing on making its voice platform more decisive. According to a CNET post, the company’s speech technology has gotten increasingly more capable of figuring out what people are saying and allowing them to do voice-powered searches and commands on devices other than phones. Now, the company wants to achieve better understanding.
As powerful as the Microsoft voice platform may be upfront, it is still missing a deeper understanding of the true meaning and context behind the words being said. To bridge this gap, Microsoft is building what it will call “conversational understanding (CU).
CU mixes speech, a dictionary, grammatical structures and machine learning to improve the process of figuring out what users are actually saying so the system can spit out an answer that takes into account all of those things.
Zig Serafin (News - Alert), the general manager of Microsoft's speech group, told CNET that everything the company has been doing up until now has been knowing what people are saying. If you compare it to a human, it is the same thing as having a really good ear. The next step is to get those words to do more than start a Web search, make a phone call or launch an app.
The infrastructure to try and accomplish this is made up of a handful of technologies, both consumer and enterprise and includes names such as TellMe, Bing’s 411 and the voice search on Windows Phone (News - Alert) 7. It has also popped up on the Xbox 360 as part of the Kinect.
Most of these systems are centered on finding out what users are saying and then feeding that information back into the cloud. In some cases, however, these commands can be simple enough to not need to be processed through the system.
The idea behind CU is to take all of this one step further by hooking into buckets of data to add context to user queries and figure out what the user is trying to do. As such, it isn’t just about search. And, since all of that data is in different places, an engine and service in place can help to look for data wherever it may live.
Of course, there is work to do to accomplish what Microsoft is hoping to accomplish and it won’t be an easy task. And, as Google (News - Alert) is working on very similar technology, it will be interesting to see who brings it to market first.
Susan J. Campbell is a contributing editor for TMCnet and has also written for eastbiz.com. To read more of Susan’s articles, please visit her columnist page.
Edited by Erin Monda