Apple’s iPhone 4S debuts this week but how does its Siri voice assistant compare to Microsoft’s Windows Phone speech features?
Microsoft has been working hard to bring more natural and intuitive speech technologies to a wider audience. The software giant introduced some of its Tellme work with the Xbox 360 and Kinect. The Tellme service currently processes over 11 billion voice interactions a year. The interactions help Microsoft improve their speech service as the system continuously learns and adapts. Windows Phone 7.5 contains an improved version of Tellme that now dictates messages and the following features:
- Making a phone call by name or nickname
- Redialing a number
- Calling voicemail
- Searching Bing
- Turning on the speakerphone
- Starting an app while in a call
- Navigating Maps
The improvements have been largely over looked in Microsoft’s Windows Phone 7.5 update, thanks to the large number of new features elsewhere in the operating system. With the release of the iPhone 4S, Apple brings a powerful new natural voice interaction to mobile devices. Microsoft’s Tellme technology is more of a command driven feature of Windows Phone right now but the company has plans to improve this in future. “We aspire to deliver services that are just as natural and easy as human conversation,” said Microsoft’s Tellme general manager Zig Serafin, in a feature post on the future of speech earlier this year. “We see a future where the service will know you: know your intent, your social and business connections, your likes and dislikes, your privacy preferences, and the things that define the context that’s important to you.”
Microsoft’s future Tellme speech recognition is a lot more personal and more aligned with Apple’s Siri features. Microsoft demonstrated some of its future speech recognition in Windows Phone in August. A video demonstration (YouTube) shows off a much improved speech interface that will work across devices. “We envision a future where we build on the experiences we deliver today with Kinect for Xbox 360, Windows Phone, or Bing for iPad or iPhone apps, by enhancing the speech NUI experience to understand more layers of context: what you are doing,” says Serafin.
The current implementation in Windows Phone 7.5 is basic in comparison to Siri’s artificial intelligence but it matches Apple’s features in some key scenarios. The ability to dictate SMS messages and reply with your voice is important at times when using your hands isn’t an option, driving a car for example. It remains to be seen just how popular services like Siri and Tellme will be amongst consumers. Speech technology is clearly adapting to modern life but its use will be limited to events where it’s necessary. I don’t expect hordes of people will be asking their phone what the weather is like during a busy commute on a public train. Microsoft’s vision of speech across multiple devices that remember your historical preferences and likes/dislikes is a powerful one. If the company is able to realise its vision with Windows 8, Xbox Next and Windows Phone 8 then it could create a key differentiation from its competitors.
Check-out the video below to see how Windows Phone 7.5 handles speech.