Somerville, MA, United States of America

Shaun Nidhiri Joseph


Average Co-Inventor Count = 4.2

ph-index = 3

Forward Citations = 162(Granted Patents)


Company Filing History:


Years Active: 2018-2019

Loading Chart...
4 patents (USPTO):

Title: Innovations of Shaun Nidhiri Joseph

Introduction

Shaun Nidhiri Joseph is an accomplished inventor based in Somerville, MA (US). He has made significant contributions to the field of automatic speech recognition through his innovative patents. With a total of 4 patents, Shaun has demonstrated his expertise and commitment to advancing technology.

Latest Patents

Shaun's latest patents focus on compressed finite state transducers for automatic speech recognition. His work on compact finite state transducers (FSTs) aims to reduce the size of FSTs used at runtime, potentially making them 50% smaller in terms of memory size. This reduction in size helps to minimize the computing resources required to operate the FSTs. Shaun's innovative approach includes compacting individual arcs and states of each FST by binning individual weights, which decreases the number of bits needed for each weight. Additionally, certain fields, such as the next state ID, may be omitted from a compact FST if an estimation technique can be employed to reproduce the next state during runtime. Portions of the FSTs can be decompressed for processing by an ASR engine, further enhancing efficiency.

Career Highlights

Shaun Nidhiri Joseph is currently employed at Amazon Technologies, Inc., where he continues to push the boundaries of technology in his field. His work has garnered attention for its practical applications and innovative solutions.

Collaborations

Some of Shaun's notable coworkers include Ariya Rastrow and Gautam Tiwari, who contribute to the collaborative environment at Amazon Technologies, Inc.

Conclusion

Shaun Nidhiri Joseph's contributions to automatic speech recognition through his patents reflect his dedication to innovation and technology. His work not only enhances the efficiency of speech recognition systems but also showcases the potential for future advancements in the field.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…