Fujitsu speech synthesis technology can convey information in a tone that is appropriate for the usage scenario
Fujitsu today announced the development of speech synthesis technology that can create a variety of high-quality synthetic voices in a short period of time, and that can convey information in a tone that is appropriate for the usage scenario or usage environment. Current speech synthesis technology, widely employed in society, is able to read-out a variety of texts, but in a monotone voice. For this reason there is a need for synthesized speech to be able to convey spoken text to listeners in accordance with the given circumstances, making it easy to understand.
The tone in the Fujitsu speech synthesis technology can be synthesized to fit the circumstances of the situation in which it is being used. In addition, voices that have a high-level of clarity can be created in a short period of time – approximately 1/30th of the time required using previous technologies.
As a result, speech can be conveyed according to the situation, such as using an alarming tone in emergencies, for example, or, when in a noisy environment, conveying information in a voice that resonates clearly. Moreover, voices that match a customer’s expected preference, such as voices that are perceived to be endearing, or distinctive voices for particular characters, can be quickly created with high quality, making it easy to use synthesized speech in a wide variety of scenarios.