David Teh-hwa Kao

Title: Innovations of David Teh-hwa Kao

Introduction

David Teh-hwa Kao is a prominent inventor based in San Francisco, CA. He has made significant contributions to the field of speech synthesis, holding a total of 5 patents. His work focuses on enhancing the expressiveness and efficiency of audio signal generation.

Latest Patents

One of his latest patents is titled "Variational embedding capacity in expressive end-to-end speech synthesis." This method involves estimating an embedding capacity by receiving a reference audio signal and determining a corresponding reference embedding. The process includes measuring reconstruction losses to estimate the capacity of the reference embedding. Another notable patent is "Controlling expressivity in end-to-end speech synthesis systems." This system generates an output audio signal by utilizing a context encoder, a text-prediction network, and a text-to-speech model to produce expressive speech with specific prosody and style.

Career Highlights

David is currently employed at Google Inc., where he continues to innovate in the field of speech technology. His work has been instrumental in advancing the capabilities of text-to-speech systems, making them more expressive and user-friendly.

Collaborations

He has collaborated with notable coworkers such as Eric Dean Battenberg and Daisy Stanton, contributing to various projects that enhance speech synthesis technologies.

Conclusion

David Teh-hwa Kao's contributions to speech synthesis through his innovative patents and work at Google Inc. highlight his role as a leading inventor in this field. His efforts continue to shape the future of expressive audio technologies.