The sound simulation technology of the Silicon Valley start-up may cause the voice actors to lose th tianbi

The Silicon Valley start-up sound simulation technology may make the voice actor unemployment in April this year, Baidu Sina and Li Gen Leslie Cheung’s 1 daily Mandarin voice data, complete the dead star "sound reproduction". This technology is mainly based on the machine to understand and deal with natural language, as long as the machine through the study of the voice of the language, you can generate a language model to achieve the pronunciation of the specified characters. The sound simulation technology is developing rapidly, and is not a giant game. Sina science and technology, located in the United States, the start-up company ObEN California, can provide a fast and accurate simulation of electronic sound technology. Users only need to read two minutes by the ObEN specified text, they can be simulated audio, and used in singing, reciting, with all conceivable language to do everything possible. The ObEN team another 3D image reconstruction technique can quickly establish 3D face model for consumers through a self portrait, that between the virtual world and the real world distance further. ObEN co-founder Nikhil Jain and Adam Zheng simulation technology to bring new voices to the sound simulation technology, there are many moving future blueprint. For example, the small family friend recorded voice, and the voice model, may persist until he grew up, also said the new content such as movies; in foreign theaters, can be used by the star of the original sound and the production of foreign language dubbing, let their own voice can be smoothly and to "export"; Fashion bloggers, South Korea, Europe and the United States alone interview star, even fashion bloggers to enter India, Turkey and even Africa, can easily conduct interviews with the local language. In addition, people separated from their families, but also through this technology, in various types of smart devices to hear the familiar voice of their loved ones. Tianya Zorpia, is no longer a kind of imagination. These blueprints let ObEN have successfully and various industries and enterprises reached a cooperation intention, including toy companies to develop smart toys with the largest, with Hollywood’s biggest movie companies and dubbing companies and so on. Although there are more than a variety of predictable blueprint, analog audio technology, it sounds a bit abstract. Specifically, ObEN is to do so to provide consumers with a variety of use of voice. First, the industry’s leading technology greatly reduces the training time of the sound model. In other words, consumers only need to spend 2-3 minutes to read the specified text, ObEN will be able to learn the technology of artificial intelligence in the field of the machine, the production of the consumer’s exclusive tone model. It’s like everyone has unique fingerprints, ObEN can get through deep learning, each user’s voice". You know, now all of the market’s exclusive sound model is only a few people can experience, and take several days, or even weeks of data entry. Moreover, with this tone model, ObEN can do so that consumers of their own electric sound, with Chinese, Japanese, Korean, is.相关的主题文章: