Tokyo--Toshiba Corporation today announced the development of multi-language speech synthesis middleware that delivers text-to-speech with a clarity and natural intonation that approximates that of the human voice. The middleware supports 9 languages -- Japanese, American English, British English, French, German, Spanish, Italian, Dutch and Mandarin -- and makes only limited demands on memory and processing power, suiting it for incorporation in car navigation systems and personal digital assistants.

Toshiba plans to commercialize the middleware by the end of fiscal year 2002.

Toshiba is a leader in speech synthesis software. The Japanese-language speech synthesis system the company delivered in 1999 set new standards for high-fidelity sound and reduced demands on memory. It has already been applied to a wide range of software for PCs, PDAs and car navigation systems, and is an integral part of recently-announced Xbox game software for the Japanese market from Microsoft Corporation.

Technology developed for the Japanese system has been applied to the new software and its support for multiple languages. The market for text-to-speech software is growing in such areas as computing, car navigation and integration in home appliances. In Japan, most car navigation systems now provide spoken directions, advice and warnings. Until recently, such systems have relied on recorded narration, which is less efficient in terms of production and requires provision of speech content by professional actors. The world market for car navigation systems is expanding rapidly, and Toshiba's new system is expected to prove particularly attractive to makers in Europe, who can use the same middleware in systems destined for different countries.

The new speech synthesis middleware complements Toshiba's multilingual speech recognition software. These can combine with the company's RISC microprocessor to provide a one-stop solution for speech recognition and synthesis system.

Toshiba is determined to reinforce its leadership in speech processing systems on a global basis, and supports this resolve with an international network of R&D bases working in this area. In October 2001, the Toshiba R&D center in China started work in this area, and this month Toshiba will establish a dedicated speech technology research team at the Cambridge Research Laboratory of Toshiba Research Europe Limited, in U.K. The two centers will collaborate with the Corporate R&D center in Japan to promote advances in high-performance multilingual speech middleware systems.