Milpitas, CA, United States of America

Jayaraman Jayaraman Thiagarajan

This inventor holds 16 USPTO granted patents and 1 published patent application, primarily in Deep Learning Applications. Top assignees: Lawrence Livermore National Security, LLC, Arizona State University. Active years: 2017-2024.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Jayaraman Jayaraman Thiagarajan. Retrieved from https://idiyas.com/inventor/jayaraman-jayaraman-thiagarajan

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 16 

% Patents Active = 87.5

Average Co-Inventor Count = 3.6

ph-index = 4

Forward Citations = 36(Granted Patents)


Location History:

  • Livermore, WA (US) (2017 - 2019)
  • Livermore, CA (US) (2020)
  • Milpitas, CA (US) (2021 - 2023)
  • Dublin, CA (US) (2017 - 2024)

Company Filing History:


Years Active: 2017-2024

Loading Chart...
Areas of Expertise:
Audio Source Separation
Deep Learning
Multi-Scale Feature Learning
Generative Priors
Attention Models
Multimodal Graph
Time Series Analysis
Image Analysis
Kernel Machines
Tumor Segmentation
Speaker Diarization
Sparse Models
16 patents (USPTO):Explore Patents

Title: Innovations by Jayaraman Jayaraman Thiagarajan: A Pioneer in Audio Source Separation

Introduction

Jayaraman Jayaraman Thiagarajan is a distinguished inventor based in Milpitas, California. With an impressive portfolio of 16 patents, he has made significant contributions to the field of audio processing, specifically in audio source separation techniques. His work aims to enhance how we understand and manipulate sound sources, showcasing innovative methods that blend technical skill with inventive thinking.

Latest Patents

Among his latest patents, several noteworthy innovations stand out. One of his prominent inventions is entitled "Systems and methods for audio source separation via multi-scale feature learning." This patent presents various embodiments of a system and methods aimed at effectively separating audio sources using advanced feature learning techniques. Another cutting-edge invention is "Systems and methods for unsupervised audio source separation using generative priors." This patent elaborates on a novel approach to audio source separation that utilizes generative priors trained on individual sound sources. By employing projected gradient descent optimization, Thiagarajan's method enables the simultaneous search in source-specific latent spaces, leading to superior recovery of constituent audio sources. Notably, while generative priors can be defined in the time domain, his findings suggest that defining them in the spectral domain results in notably high-quality source estimates.

Career Highlights

Throughout his career, Thiagarajan has worked with leading institutions, including Lawrence Livermore National Security, LLC, and Arizona State University. His roles at these organizations have allowed him to collaborate on pioneering research and development efforts in audio processing and signal separation technologies.

Collaborations

Jayaraman Jayaraman Thiagarajan has also collaborated with esteemed professionals in his field, including Andreas Spanias and Peer-Timo Bremer. These collaborations have enriched his research and have resulted in advancements in audio technology through the sharing of knowledge and expertise.

Conclusion

Jayaraman Jayaraman Thiagarajan exemplifies the spirit of innovation through his numerous patents and collaborations in audio source separation. His work not only contributes to academic knowledge but also paves the way for practical applications in various industries, showcasing the importance of continual innovation in technology.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…