Montreal, Canada

Devang Kulshreshtha

USPTO Granted Patents = 1 

Average Co-Inventor Count = 9.0

ph-index = 1


Company Filing History:


Years Active: 2025

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Devang Kulshreshtha: Innovator in Speech Recognition Technology

Introduction

Devang Kulshreshtha is a notable inventor based in Montreal, Canada. He has made significant contributions to the field of automatic speech recognition. His innovative work focuses on removing bias from speech recognition models, enhancing their accuracy and reliability.

Latest Patents

Devang holds a patent titled "Removing bias from automatic speech recognition models using internal language model estimates." This patent addresses the issue of bias in automatic speech recognition model predictions. The method involves processing audio data through an automatic speech recognition model to generate original word token predictions. By masking portions of the audio data, additional word token predictions can be produced. A comparison of these predictions allows for the estimation of an internal language model, which can then be used to modify the original predictions, effectively removing lexical bias and improving speech prediction accuracy.

Career Highlights

Devang Kulshreshtha is currently employed at Amazon Technologies, Inc. His role involves leveraging his expertise in speech recognition technology to develop advanced solutions. His work is instrumental in enhancing the performance of automatic speech recognition systems.

Collaborations

Devang collaborates with talented individuals such as Nilaksh Das and Monica Lakshmi Sunkara. Together, they contribute to innovative projects that push the boundaries of speech recognition technology.

Conclusion

Devang Kulshreshtha's contributions to the field of automatic speech recognition are noteworthy. His innovative patent and collaborative efforts at Amazon Technologies, Inc. highlight his commitment to advancing technology in this area. His work continues to pave the way for more accurate and reliable speech recognition systems.

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