Fujitsu Laboratories development of speech interface technology which enables users to retrieve a variety of information by simply speaking into a smartphone, without having to look at the smartphone’s display.
After listening to a synthesised speech read the latest news and other information, users can articulate the information that they would like to learn more aboutand then the software will read the details about the topic and the related information, said Fujitsu.
The company said the new technology is a eyes- and hands-free speech interface in which, by simply speaking about what the user is interested in, the system pulls up relevant information and reads it out loud.
The technology automatically extracts the orthographic patterns of new terminology from text found on the Internet and inputs it into the system’s vocabulary dictionary to create a speech interface which minimises often misread and falsely recognised words, said Fujitsu.
Fujitsu said the speech technology analyses the previously presented information by the system, extracts vocabulary focused on certain topics, and generates a speech recognition dictionary automatically by which the system can correctly recognise homonyms and other ambiguous phrases to deliver accurate dialogue with the user.
As a part of the datacentre-based speech recognition and speech synthesis process the technology absorbs the delays caused by processing and transmission, by dividing and anticipating speech data and the technology improves the quality of the response time by controlling the timing of breaks between words, said the company.
The Japan-based company said with the new technology users can retrieve information through a series of intuitive speech interaction, without looking at any displays.
