This inventor holds 1 USPTO granted patent. Top assignee: Lucent Technologies Inc.. Active years: 2001.
Company Filing History:
Years Active: 2001
Title: Michael Sean Fee: Innovator in Speech Processing Technology
Introduction
Michael Sean Fee is a notable inventor based in New Vernon, NJ (US). He has made significant contributions to the field of speech processing, particularly in the area of speech recognition and coding. His innovative techniques have the potential to enhance the accuracy and efficiency of speech-related technologies.
Latest Patents
Michael Sean Fee holds a patent for a speech processing technique that focuses on obtaining an intermediate set of frequency-dependent features from a speech signal. This technique utilizes multiple tapers derived from Slepian sequences to create a product of the speech signal and the Slepian functions. By obtaining multiple tapered Fourier transforms from this product, he calculates a set of frequency-dependent features. In one preferred embodiment, a derivative of the cepstrum of the speech signal is used to estimate the pitch of the speech signal. Additionally, the F-spectrum is calculated from the product, leading to the F-cepstrum, which provides pitch estimation through the maximum of the F-cepstrum.
Career Highlights
Michael Sean Fee has worked at Lucent Technologies Inc., where he has applied his expertise in speech processing. His work has contributed to advancements in technologies that rely on accurate speech recognition and coding. His innovative approach has positioned him as a key figure in the field.
Collaborations
Throughout his career, Michael has collaborated with notable colleagues, including Ching Elizabeth Ho and Partha Pratim Mitra. These collaborations have further enriched his work and contributed to the development of cutting-edge technologies in speech processing.
Conclusion
Michael Sean Fee's contributions to speech processing technology demonstrate his innovative spirit and dedication to advancing the field. His patented techniques have the potential to significantly impact speech recognition and coding technologies.
