Mountain View, CA, United States of America

David G Grangier

This inventor holds 10 USPTO granted patents and 3 published patent applications and 4 EPO patents. Top assignees: Google Inc., Nec Laboratories America, Inc., Meta Platforms, Inc.. Active years: 2012-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: David G Grangier. Retrieved from https://idiyas.com/inventor/david-g-grangier-awq292am

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

Calculating rank
USPTO Granted Patents = 10 

% Patents Active = 80.0

 

Average Co-Inventor Count = 3.1

ph-index = 3

Forward Citations = 28(Granted Patents)


Location History:

  • Princeton, NJ (US) (2012 - 2013)
  • San Francisco, CA (US) (2014)
  • Mountain View, CA (US) (2020 - 2024)

Company Filing History:


Years Active: 2012-2026

Loading Chart...
Loading Chart...
10 patents (USPTO):Explore Patents

Title: The Innovative Contributions of David G Grangier

Introduction

David G Grangier is a prominent inventor based in Mountain View, CA. He has made significant contributions to the field of audio processing and speech separation. With a total of 10 patents to his name, Grangier's work has had a substantial impact on how audio signals are processed and understood.

Latest Patents

One of Grangier's latest patents focuses on separating speech by source in audio recordings. This innovative method predicts isolated audio signals conditioned on speaker representations. The process involves obtaining a recording that includes speech from multiple speakers and utilizing a speaker neural network to generate per-recording speaker representations. These representations capture the features of each identified speaker, allowing for the generation of predicted isolated audio signals corresponding to each speaker's speech.

Another notable patent involves generating audio using auto-regressive generative neural networks. This method includes receiving a request to generate an audio signal and obtaining a semantic representation of that signal. By employing generative neural networks, the acoustic representation of the audio signal is created, which is then processed using a decoder neural network to produce the final audio prediction.

Career Highlights

Throughout his career, David G Grangier has worked with leading technology companies, including Google Inc. and Facebook, Inc. His experience in these organizations has allowed him to collaborate with some of the brightest minds in the industry, further enhancing his innovative capabilities.

Collaborations

Grangier has had the opportunity to work alongside talented individuals such as Neil Zeghidour. These collaborations have contributed to the advancement of his research and the successful development of his patents.

Conclusion

David G Grangier's contributions to audio processing and speech separation are noteworthy. His innovative patents and collaborations with leading companies and talented individuals highlight his significant impact in the field. Grangier continues to push the boundaries of technology, making strides that benefit various applications in audio processing.

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…