Yan Deng

Title: Yan Deng - Innovator in Neural Text-to-Speech Synthesis

Introduction

Yan Deng is a prominent inventor based in Redmond, WA (US). He has made significant contributions to the field of neural text-to-speech synthesis. His innovative work has the potential to enhance the way machines generate human-like speech.

Latest Patents

Yan Deng holds a patent for a method titled "Multi-speaker neural text-to-speech synthesis." This patent describes a process for generating speech through multi-speaker neural text-to-speech (TTS) synthesis. The method involves receiving a text input and providing speaker latent space information of a target speaker through at least one speaker model. Additionally, it predicts at least one acoustic feature based on the text input and the speaker latent space information. Finally, a speech waveform corresponding to the text input is generated through a neural vocoder based on the predicted acoustic feature and speaker latent space information. Yan Deng has 1 patent to his name.

Career Highlights

Yan Deng is currently employed at Microsoft Technology Licensing, LLC. His work at Microsoft has allowed him to explore and develop advanced technologies in speech synthesis. His contributions are recognized within the industry for their innovative approach to TTS systems.

Collaborations

Yan collaborates with Lei He, a talented woman in the field. Their partnership exemplifies the importance of teamwork in driving innovation and achieving breakthroughs in technology.

Conclusion

Yan Deng is a key figure in the advancement of neural text-to-speech synthesis. His patent and work at Microsoft Technology Licensing, LLC highlight his commitment to innovation in this exciting field.