IDiyas

For the Inventor, By the Inventor

Dublin, CA, United States of America

Khe Chai Sim

USPTO Granted Patents = 17 

 

Average Co-Inventor Count = 3.9

ph-index = 3

Forward Citations = 15(Granted Patents)


Location History:

  • Dublin, CA (US) (2021 - 2024)
  • Cupertino, CA (US) (2022 - 2024)

Company Filing History:

goldMedal17 out of 32,429 
 
Google Inc.
 patents

Years Active: 2021-2025

where 'Filed Patents' based on already Granted Patents

17 patents (USPTO):
1. 12456033 - Multi-stream recurrent neural network transducer(s) (2025-10-28),
2. 12431122 - Training a language model of an end-to-end automatic speech recognition model using random encoder features (2025-09-30),
3. 12424206 - Context-aware neural confidence estimation for rare word speech recognition (2025-09-23),
4. 12417757 - On-device speech synthesis of textual segments for training of on-device speech recognition model (2025-09-16),
5. 12347419 - Unsupervised federated learning of machine learning model layers (2025-07-01),
6. 12254865 - Multi-dialect and multilingual speech recognition (2025-03-18),
7. 12249317 - Joint unsupervised and supervised training for multilingual ASR (2025-03-11),
8. 12223952 - Generation and utilization of pseudo-correction(s) to prevent forgetting of personalized on-device automatic speech recognition (ASR) model(s) (2025-02-11),
9. 12126845 - Ephemeral learning of machine learning model(s) (2024-10-22),
10. 12073319 - Sound model localization within an environment (2024-08-27),
11. 12014724 - Unsupervised federated learning of machine learning model layers (2024-06-18),
12. 11978432 - On-device speech synthesis of textual segments for training of on-device speech recognition model (2024-05-07),
13. 11900915 - Multi-dialect and multilingual speech recognition (2024-02-13),
14. 11705106 - On-device speech synthesis of textual segments for training of on-device speech recognition model (2023-07-18),
15. 11545133 - On-device personalization of speech synthesis for training of speech model(s) (2023-01-03),

Title: Khe Chai Sim: Innovator in Automatic Speech Recognition

Introduction

Khe Chai Sim is a prominent inventor based in Dublin, California, known for his significant contributions to the field of automatic speech recognition. With a total of 16 patents to his name, he has made remarkable advancements in technology that enhance the efficiency and accuracy of speech recognition systems.

Latest Patents

One of Khe Chai Sim's latest patents is titled "Training a language model of an end-to-end automatic speech recognition model using random encoder features." This innovative method involves obtaining a training text sample that is not paired with corresponding audio data. It generates a sequence of pseudo-random encoder variables and processes them using a decoder of a sequence transduction model to predict a probability distribution over possible output labels. The method further includes determining a loss-based metric based on the training text sample and the predicted probability distribution, ultimately training the decoder based on this loss metric.

Another notable patent is "Context-aware neural confidence estimation for rare word speech recognition." This automatic speech recognition (ASR) system comprises an ASR model, a neural associative memory (NAM) biasing model, and a confidence estimation model (CEM). The ASR model encodes a sequence of audio frames into higher-order feature representations and outputs a final speech recognition result. The NAM biasing model modifies these representations based on contextual information, while the CEM computes the confidence of the final result.

Career Highlights

Khe Chai Sim is currently employed at Google Inc., where he continues to push the boundaries of speech recognition technology. His work has been instrumental in developing systems that improve user interaction with devices through more accurate speech recognition capabilities.

Collaborations

Throughout his career, Khe Chai Sim has collaborated with notable colleagues, including Françoise Beaufays and Johan Schalkwyk. These collaborations have fostered an environment of innovation and creativity, leading to groundbreaking advancements in the field.

Conclusion

Khe Chai Sim's contributions to automatic speech recognition have significantly impacted the technology landscape. His innovative patents and collaborative efforts at Google Inc. continue to shape the future of how we interact with machines through speech.

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