This inventor holds 1 USPTO granted patent. Top assignee: International Business Machines Corporation. Active years: 1995.
Company Filing History:
Years Active: 1995
Title: P S Gopalakrishnan: Innovator in Speech Recognition Technology
Introduction
P S Gopalakrishnan is a notable inventor based in Yorktown Heights, NY (US). He has made significant contributions to the field of speech recognition technology. His innovative work has led to the development of a patent that enhances the accuracy of speech labeling in context-dependent systems.
Latest Patents
Gopalakrishnan holds a patent titled "Labelling speech using context-dependent acoustic prototypes." This invention addresses the challenges of labeling speech in a context-dependent speech recognition system. The method involves aligning the phone context of a speech frame with the appropriate acoustic parameter vector. By utilizing context-independent acoustic prototypes, the invention simplifies the alignment process, making it more efficient. The phonetic context of each phone is known, allowing for accurate tagging of acoustic parameter vectors with corresponding phonetic contexts. The invention determines the probability of achieving tagged acoustic parameter vectors, ultimately associating the label with the highest probability to the context-dependent acoustic parameter vector.
Career Highlights
Gopalakrishnan is associated with the International Business Machines Corporation (IBM), where he has contributed to various projects in speech recognition and related technologies. His work has been instrumental in advancing the capabilities of speech recognition systems.
Collaborations
Throughout his career, Gopalakrishnan has collaborated with esteemed colleagues, including Lalit R Bahl and Peter V De Souza. These collaborations have further enriched his contributions to the field.
Conclusion
P S Gopalakrishnan's innovative work in speech recognition technology exemplifies the impact of dedicated inventors in advancing communication systems. His patent demonstrates a significant step forward in the accuracy and efficiency of speech labeling.
