The handset, made by Fujitsu Ltd, contains new & proprietary technology to enter e-mail text using remote speech recognition. If the "voice input" button in the e-mail editing display is pressed, software that extracts the characteristics of the user's speech (and performs Analog-to-Digital conversion) will start, and access the DoCoMo's i-mode site.
When users say what they want transcribed into an email, the in-box software sends the dictation to the i-mode server. There, speech recognition software manufactured by Advanced Media Inc outputs transcribed text. The F884i receives the transcribed text, displays it in the email's text display interface.
As best we can tell, without a direct response from DoCoMo or Advanced Media - This appears to be DSR (Distributed Speech Recognition) which we've blogged about in the past; and we are tremendous fans of DSR as a global answer to near-perfect mobile speech recognition.
We've also emailed David Pearce, founder and Chief Developer of this emerging technology to see if he has any information on whether this may, in fact be DSR..
Check back later for details!
Labels: Distributed Speech Recognition, DoComo, Fujitsu, mobile speech recognition, remote speech recognition
posted by The Team @ 6:48 AM
RSS Feed
Subscribe via Feedburner
1 Comments:
I spoke to President (and soon chairman) Suzuki of Advanced Media last week about DSR and the handset by Fujitsu uses the Fujitsu/AM DSR and not the ETSI Standard that has been implemented on other DoCoMo 905i series phones and all future FOMA phones in Japan. Very nifty indeed!
Post a Comment
<< Home