Microsoft 2020 International Day of Persons with Disabilities special event: AI makes audiobooks more vivid

      On the afternoon of December 2, Microsoft held a special event in Beijing to celebrate the 2020 International Day of Persons with Disabilities, showcasing the latest progress in Microsoft's AI voice technology - neural network voice intelligence. Neural network voice intelligence has the ability to produce multiple timbres and emotions, and can be quickly produced through the creative platform. At the same time, a donation ceremony for the audio content of Hong Dandan's "Library in the Heart" was also held at the event.

Microsoft Global Senior Vice President Hong Xiaowen

　　During the event, Dr. Hsiao-Wen Hong, Microsoft's global senior vice president, chairman of Microsoft Asia Pacific R&D Group and director of Microsoft Research Asia, delivered a keynote speech. Hsiao-Wen Hong first emphasized Microsoft's mission of "empowering every person and every organization in the world to achieve extraordinary results". In 2020, the technology sector contributed about 5% to the global GDP, and it is expected to reach 10% by 2030. Microsoft will also continue to be committed to using inclusive technology to achieve everyone and bring products and services to everyone. Artificial intelligence will continue to make the world a better place from six aspects: Earth Plan, Technology Accessibility, Humanitarian Action Plan, Cultural Heritage Protection Technology, and Health and Medical Technology.

Microsoft Global Technical Fellow Huang Xuedong

　　Subsequently, Dr. Xuedong Huang, Microsoft Global Technology Fellow and Chief Technology Officer of Microsoft Azure AI, also shared through a video: Thanks to the efforts of Microsoft Research Asia, Microsoft's AI voice technology has been integrated into an intelligent audio content creation platform that has both practical and promotional value, allowing people who have not been exposed to AI technology to participate in the creation of audio content, bringing richer audio content.

Hong Dandan's "Library in Mind" Audio Content Donation Ceremony

　　A donation ceremony for the audio content of Hongdandan's "Library of Mind" was also held at the event. Hongdandan's "Library of Mind" was established by Beijing Hongdandan Cultural Exchange Center (hereinafter referred to as Hongdandan) to provide audio book lending services for the blind. Zheng Xiaojie, the founder of Hongdandan, said that Hongdandan found in many blind schools that the existing books and audio content for the blind are generally old and cannot meet the reading needs of the blind. Traditional manually recorded audio content also has the disadvantages of being time-consuming and small in quantity. Cooperation with Microsoft can bring rich choices to the blind, so that books can accompany the blind throughout their lives.

Ding Binggong, Chief Product Director of Microsoft Cloud Computing and Artificial Intelligence Division

　　How to achieve vivid and rich speech synthesis? Ding Binggong, Chief Product Director of Microsoft Cloud Computing and Artificial Intelligence Division, explained the relevant technologies: Microsoft has four major advantages in speech synthesis: the most intelligent speech synthesis, the most extensive global speech coverage, flexible cloud and terminal calls, and powerful speech customization capabilities. On this basis, Microsoft launched neural network speech intelligence, which conducts neural network acoustic learning on the input text, and outputs natural audio after neural network acoustic decoding.

Neural network voice intelligence has multiple timbres and multiple emotions

　　Compared with traditional intelligent voice, neural network voice intelligence has multiple timbres and multiple emotions, making the voice content no longer monotonous. For example, neural network voice intelligence can simulate the speaking styles of various scenarios such as news broadcasts, customer service, and chats, and can add emotions such as happiness, disdain, and anger, and can achieve emotional grading to make emotions more delicate. In addition to platform voices, neural network voice intelligence can also provide voice customization services, design voices that are in line with corporate, organizational or personal brand strategies, and optimize emotions according to the scene to create a unique personality and achieve natural human-computer interaction.

Intelligent audio content creation platform

　　In actual use, the intelligent audio content creation platform created by Microsoft, through two parts: intelligent fully automatic generation mode and customized free creation mode, allows volunteers who are not familiar with AI technology to create audio content through simple operations.

"AI Voice + Public Welfare" Roundtable Dialogue

       At the end of the event, Microsoft organized two roundtable discussions on "AI Voice + Charity" and "AI Voice + Industry" to share more stories behind Microsoft's AI voice technology and Hong Dandan's charity activities.