Fujitsu Laboratories has developed speech synthesis technology in which the tone can be synthesized to fit the situation, and with which a variety of high-quality voices can be quickly created.
Instead of monotone voice, Fujitsu Laboratories has developed speech synthesis technology in which the tone can be synthesized to fit the circumstances of the situation in which it is being used. High clarity voice can be created in a short period of time of approximately 1/30th of the time required using previous technologies, says Fujitsu.
Fujitsu explains the conventional synthesis methods used thus far involved connecting large volumes of prerecorded speech waveforms. To make the synthesis process more flexible, Fujitsu Laboratories used a method to synthesize speech in which multiple characteristics, such as voice quality, intonation, and pauses, are skillfully captured and converted into parameters.