Fujitsu develops new speech synthesis tech

MANILA, Philippines - Fujitsu Laboratories Ltd., a leading Japanese information and communication technology company, has developed a new speech synthesis technology that allows the voice tone to be synthesized to suit the purpose and urgency of the message. The technology is fit for use in alarm and announcement systems around the Philippines.

The Fujitsu-developed speech synthesis technology can be used by municipal authorities for announcements in disaster-prevention situations, for which demand has been rising in recent years.

In the event of a disaster, information could be broadcast in an urgent tone, while routine local notices could be broadcast in a calm and even pitch.

This is a major leap from the current speech synthesis technology in use today, which can read a variety of texts but mainly in a monotone. The newly developed speech synthesis technology can create a variety of high-quality synthetic voices in a short period of time, and convey information in a tone that is appropriate for the scenario or environment, making it easier to comprehend.

The Fujitsu-developed technology deals with the issues of difficulty in synthesizing the voice or tone to fit the usage scenario or environment. Fujitsu’s flexible approach breaks down the synthesis into the basic components of speech, then sets parameters for these components, such as intonation and pauses, which can be quickly and easily manipulated so that an algorithm can create speech in 1/30th the time of previous methods.              

This means that the Fujitsu system can adapt synthetic speech to particular circumstances. An alarm message can sound urgent, or be designed to cut through a noisy factory floor, or be heard clearly across an airfield.

It can also be used to be reassuring, or match the image that a company wants to present to the public. Fujitsu says that since the system uses only a small number of recorded speech patterns, the technology can be adapted to portable devices, such as those used in medicine, or for recreating a person’s voice after it’s lost due to surgery or accident.

Fujitsu Laboratories says it hopes to develop a practical version of its speech synthesis system this year.