Company Filing History:
Years Active: 2005-2009
Title: Innovations by Leo Jingyu Lee in Speech Recognition Technology
Introduction
Leo Jingyu Lee is a prominent inventor based in Waterloo, Canada. He has made significant contributions to the field of speech recognition technology, holding a total of 4 patents. His work focuses on advanced methods that enhance the efficiency and accuracy of speech recognition systems.
Latest Patents
One of Leo Jingyu Lee's latest patents is titled "Method of speech recognition using variational inference with switching state space models." This innovative method involves defining a switching state space model for a continuous valued hidden production-related parameter and the observed speech acoustics. It approximates a posterior probability that provides the likelihood of a sequence of hidden production-related parameters and a sequence of speech units based on observed input values. Notably, the boundaries of the speech units are optimally determined rather than fixed. The method employs a mixture of Gaussian approximation in one embodiment and an HMM posterior approximation in another.
Another significant patent is "Method of speech recognition using multimodal variational inference with switching state space models." This method efficiently sets posterior probability parameters for a switching state space model by defining a window containing at least two but fewer than all frames. A separate posterior probability parameter is determined for each frame in the window, which is then shifted sequentially to include subsequent frames. This approach closely approximates a more rigorous solution while saving computational costs by two to three orders of magnitude.
Career Highlights
Leo Jingyu Lee is currently associated with Microsoft Technology Licensing, LLC, where he continues to innovate in the field of speech recognition. His work has garnered attention for its potential applications in various technologies, enhancing user interaction and accessibility.
Collaborations
Throughout his career, Leo has collaborated with notable professionals in the field, including Hagai Thomas Attias and Li Deng. These collaborations have contributed to the advancement of his research and the development of cutting-edge technologies.
Conclusion
Leo Jingyu Lee's contributions to speech recognition technology exemplify the impact of innovative thinking in the field. His patents reflect a commitment to enhancing the efficiency and accuracy of speech recognition systems, paving the way for future advancements.