logo

For the Inventor, By the Inventor

Sunnyvale, CA, United States of America

Chung-Cheng Chiu

This inventor holds 23 USPTO granted patents and 9 published patent applications and 8 EPO patents, primarily in Speech Recognition Technology. Top assignee: Google Inc.. Active years: 2019-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Chung-Cheng Chiu. Retrieved from https://idiyas.com/inventor/chung-cheng-chiu

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

USPTO Granted Patents = 23 

% Patents Active = 95.7

 

Average Co-Inventor Count = 5.8

ph-index = 4

Forward Citations = 35(Granted Patents)


Location History:

  • Mountain View, CA (US) (2019 - 2024)
  • Sunnyvale, CA (US) (2020 - 2024)

Company Filing History:

goldMedal23 out of 33,920 
 
Google Inc.
 patents

Years Active: 2019-2026

Loading Chart...
Loading Chart...
Areas of Expertise:
Acoustic Echo Cancellation
Speech Enhancement
Voice Separation
Attention Mechanisms
Neural Networks
Sequence-to-Sequence Models
Low-Latency ASR
Machine Learning
Audiographic Images
Word Error Rate Training
Cascaded Encoders
Transformer Models
23 patents (USPTO):Explore Patents
1. 12731575 - Attention-based joint acoustic and text on-device end-to-end model (2026-09-08),
2. 12482455 - Systems and methods for training dual-mode machine-learned speech recognition models (2025-11-25),
3. 12444408 - Two-pass end to end speech recognition (2025-10-14),
4. 12373666 - Convolution-augmented transformer models (2025-07-29),
5. 12175202 - Enhanced attention mechanisms (2024-12-24),
6. 12154581 - Cascaded encoders for simplified streaming and non-streaming ASR (2024-11-26),
7. 12119014 - Joint acoustic echo cancelation, speech enhancement, and voice separation for automatic speech recognition (2024-10-15),
8. 12106749 - Speech recognition with sequence-to-sequence models (2024-10-01),
9. 12094453 - Fast emit low-latency streaming ASR with sequence-level emission regularization utilizing forward and backward probabilities between nodes of an alignment lattice (2024-09-17),
10. 12079703 - Convolution-augmented transformer models (2024-09-03),
11. 11922932 - Minimum word error rate training for attention-based sequence-to-sequence models (2024-03-05),
12. 11816577 - Augmentation of audiographic images for improved machine learning (2023-11-14),
13. 11804212 - Streaming automatic speech recognition with non-streaming model distillation (2023-10-31),
14. 11646019 - Minimum word error rate training for attention-based sequence-to-sequence models (2023-05-09),
15. 11625572 - Recurrent neural networks for online sequence generation (2023-04-11),

Title: Innovations of Chung-Cheng Chiu in Speech Recognition Technology

Introduction

Chung-Cheng Chiu is an accomplished inventor based in Sunnyvale, CA, with a notable portfolio that includes 19 patents. His work primarily focuses on automated speech recognition (ASR) technologies, contributing significantly to advancements in the field.

Latest Patents

Chiu's latest innovations include two groundbreaking patents. The first, titled "Enhanced Attention Mechanisms," describes a method for processing a sequence of audio features using an encoder neural network. This method involves generating encodings from audio features and applying a hard monotonic attention output to select and focus on relevant encodings. It emphasizes the generation of a context vector to predict output labels effectively.

The second patent, "Cascaded Encoders for Simplified Streaming and Non-Streaming ASR," introduces an ASR model that incorporates a first and second encoder alongside a decoder. This model processes acoustic frames and higher-order feature representations to generate accurate probability distributions over various speech recognition hypotheses at each time step, thus enhancing the efficiency of speech recognition systems.

Career Highlights

Chung-Cheng Chiu has worked extensively in the realm of speech technologies and has played a crucial role in developing models that improve the accuracy and efficiency of automated speech recognition. His patents not only showcase his technical expertise but also indicate his ongoing commitment to innovation in the tech industry.

Collaborations

Chiu collaborates with prominent professionals in his field, including Yonghui Wu and Tara N Sainath, both of whom contribute to the development of advanced speech recognition systems at Google Inc. Their collective efforts mark significant strides in enhancing automated communication technologies.

Conclusion

Chung-Cheng Chiu's contributions to automated speech recognition reflect his innovative spirit and technical prowess. With ongoing advancements in his work, Chiu continues to shape the future of speech technologies, positioning himself as a key inventor in this exciting field.

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…