Development of Speech Recognition Technology for Smartphone by Fujitsu
Fujitsu Laboratory has announced the development of a speech interface technology which would allow its users to access multitude of information by simply talking to their smartphone, and not having to look at the smartphone’s display. With introduction and wide spread of touch/multi-touch capable screen as well as other type of tactile/Haptic technology based screens, it is essential for its user to both touch and view the screen of smartphone while interacting with it. However mobile devices which are used for other type of situations such as walking, driving as well as working need to allow the users to keep their eyes and hands focused on their given task, making speech recognition an ideal interface for mobile devices, where the mobile device is capable of understanding human speech, and at the same time the device is able to read the text back to its user in aloud voice through its speech synthesis technology. The newly developed technology by Fujitsu Laboratory with its high-quality speech synthesis technology, as well as speech recognition technology is capable of eliminating background noises while picking up only the user’s voice.
The new technology makes it easy to receive various news and other type of information services without any needs to look or touch the handset device. Through its eyes-free and hands-free speech interface, the system fetches all the relevant information and reads out load based on user’s interest by way of speaking to the device. For example when the user speaks a particular phrase from a news headline that system has read, the system is capable of getting more detailed articles related to the topic. Well, Fujitsu’s announcement comes at the same time, when Apple announced its new iPhone 4S with its full featured voice recognition functionality called “Siri”, based on dual-core A5 chip. I hope Fujitsu’s new technology can live-up to market expectation surrounding voice recognition capable smartphones.