My 10000 yuan dubbing equipment, every dubbing actor will like - 3

My 10000 yuan dubbing equipment, every dubbing actor will like - 3
However, behind the professionalism is the high production cost and long production cycle. The input of tens of millions of levels and the recording of several years have naturally determined that the output of high-quality audio products will not be too high. The high-quality products need to be produced by professional dubbers in a longer time, and they are irreplaceable.
"Sound is a sense of touch, which helps us open a more sexy literary dimension." As Shao Yanjun, a professor of the Chinese Department of Peking University, said, users need not only "sound to fill the fragmented time", but also a better auditory experience. [Chinese dubbing]
For this problem, Shengka also gave a solution. It adopts the transfer technology across speaker styles to form the voice color model of the multi-emotional and multi-dialect voice dubber. These models use the hierarchical VAE (Variable Auto-encoder) to encode the prosodic information in the voice, decouple the voice color and prosodic information, and make the voice have character.
At present, the voice coffee can simulate dozens of novel dubbers, with rich, magnetic, gentle, friendly, mature and other different sound quality, and can speak Northeast dialect, Shaanxi dialect, Sichuan dialect, Tianjin dialect and other dialects, expressing six emotions such as happiness, anger, sadness, surprise, fear, disgust.
At the same time, the voice cafe can also intelligently identify the full text roles and assign these different voices to different roles; In addition, through the technical ability to identify the speakers and emotions of the dialogue in the article, the synthesis of multiple roles and feelings can be realized, and the combination of efficiency and high quality can be achieved.
What is more prominent is that the functions of the whole line of sound coffee are free for a limited time, supplemented by a more friendly operation interface and powerful computing power, to break through the originally shelved professional barriers.
"There will be a thousand Hamlets in the eyes of a thousand readers". Now innovative technology has given them the opportunity to create the audio books that best match their imagination. [Animation dubbing]
3. "Freedom of voice"
Whenever there is a popular work, the distribution department will coordinate resources as soon as possible to fill the gaps in categories as soon as possible, so as to cover more users' experience demands, among which audio books are an important category. [English dubbing]
There is no lack of mature cases in reality. Take the popular IP "Breaking the Sky" as an example. In 2010, the work won the popularity of many readers as soon as it was released. Immediately, the publisher launched audio books, which also achieved ideal results. Referring to the data from online sources, the cumulative broadcast volume of "Breaking the Sky" has exceeded 1 billion times.
In a sense, online literature has gone beyond the "output supply" short-term relationship of author writing and reader reading, and formed a value system of platform side * * various resources, long-term and multi-category development around mature IP to meet multiple needs. In other words, as long as the works are of high quality, you can see the corresponding audio books on the platform. The only problem is time.
When the driving force of a market growth is not the enterprise pulling ahead, but the demand pushing behind, rapid development is inevitable. According to a research institute, some upstream publishing enterprises and audio production enterprises are gradually infiltrating into the midstream audio reading business, and the midstream and midstream of the industry chain presents an integrated development trend, and the industry will usher in a period of rapid development.
The rapid development of any industry is inseparable from the iteration of production tools. For audio novels, the pure "human" production mode relying on fans and dubbing companies no longer matches the needs of industry development. "Human+AI" is the trend of the times. The emergence of various AI tools makes the creators of audio novels further away from "voice freedom". For the sound coffee, its value has never been "a toy for a small circle", but one of the production tools to achieve "sound freedom".
4. Conclusion
In a sense, the "voice coffee" voice novel dubbing function of Tencent's PCG AI interaction department is an exploration of AI in the vertical industry. Under the demand of "ear economy", the constant output of content, and the reduction of the threshold of AI, how far is it from the minority to the public?
Big water can make big fish. When the upstream "gate" is opened, copyright owners, platform owners and users in the audio novel industry chain will benefit from it.
Statement: This article is original and reprinted in part. If reprinted, please indicate the source and source. I am the editor of Voices100, a multilingual self-help live dubbing network