As the leading developer of speech and language technology in China and creator of the Chinese Speech Synthesis Markup Language, a nationally award-winning text-to-speech (TTS) system, iFlytek was chosen to provide the TTS technology for the Olympic Games. With iFlytek's technology and support, Beijing was able to achieve its goal and deliver pertinent information throughout the games. In the mid-1980s, with the support of the Chinese government, iFlytek began developing speech synthesis systems, and since has developed the most widely used system for the Chinese language worldwide. Perhaps the most daunting task for the Chinese TTS creator is that Chinese is not one language, but a group of thousands of dialects. Many of these dialects are arguably separate languages that are almost completely mutually unintelligible. Therefore, a true Chinese TTS system must incorporate hundreds of languages.
While Michael Phelps was making history in the pool, TTS was making sure people heard about it Golden Words >>> On August 8, a white figure jumping out of a background of bright red blazed across more than 2 billion television screens. Opening ceremonies of the 2008 Summer Olympic Games in Beijing had begun. For most viewers across the world, this emblem simply signified the start of the games. However, for the 383 million people watching in China, this character meant something much more complex. The figure appeared to be a man running with his arms outstretched, but it was actu- ally a stylized version of the character , the word for “capital” in Chinese. When paired with the character , which means “north,” morphs into , the word for Beijing. In the form of the red and white image, created by prominent Chinese graphic designer Guo Chunning, the symbol means “dancing Beijing,” and its red background is meant to evoke a seal symbolizing the promise of the city. The likeness to a person is meant to capture the idea of a hero. The outstretched arms mean “welcome,” and the curving lines represent the “form of a dragon.” Imagine how you would say to capture its full meaning. Imagine how this would sound in Chinese so that it could be understood by all speakers, many of whom speak dialects that are mutually unintelligible. Now imagine how would be spoken by your average text-to-speech (TTS) system. • by Jessica Sebor • NOVEMBER/DECEMBER 2008 Speech Technology | 27 AUTHORING SYNTHESIZED SPEECH For an event that was expected to TTS support for those driving or unable simple. “We did not need to do anything bring more than 2 million people to Bei- to read their screens. Bai notes that this fancy, as our TTS has been around for jing, the city spent a great deal of time, was especially important due to road clos- many years and is the best on the market energy, and money—a total of $40.9 mil- ings that changed daily. “The mapping for Chinese,” he says. lion—to ensure it was prepared. A key- information was a very strong part—to be After the prototype was approved in stone in this preparation was the goal able to tell you the traffic is being con- 2005 by the BOCOG, little customization laid out in the Action Plan for the trolled so if you want to go here, you need was needed outside of providing addi- Olympic Games, created by the Beijing to use this other road,” he says. tional TTS engines and completing test- Organizing Committee for the Games of 2) Services for visitors to receive ing to ensure that the engines worked the XXIX Olympiad (BOCOG): “That information related to the games as well properly. “Very standard work,” Bai says. anybody, at any time and in any place, as tourism support were also needed. However, to understand how it was can enjoy the information service that is Delivered via kiosks set up around the possible for (Welcome to affordable, comprehensive, personalized, city, on handhelds, and through the offi- Beijing) to be heard with a click of a but- and multilingual.” cial Beijing Olympics Web site, iFlytek’s ton throughout China’s capital city on This was no small task considering TTS was used to make this information August 8, we must look back several the volume of information that had to accessible via audio delivery. decades to the creation of this technology be delivered to staff, sponsors, volun- 3) Information and training services and back nearly 3,000 years at one of the teers, athletes, guests, and tourists. To for volunteers needed to be delivered. oldest, most complex, and most rapidly make good on its promise, Beijing Beijing recruited more than 5,000 volun- changing languages in the world today. needed to have information available teers to support media operations, act as not only visually, but audibly as well for VIP escorts, and provide translations, The Hurdles those who could not read, could not see, medical help, directions, and more. TTS The first speech synthesis devices built or were on the go. However, extremely was used in kiosks, call centers, and on a for a computer were developed in
Pages to are hidden for
"GOLDEN WORDS"Please download to view full document