Location History:
- SanSan Francisco, CA (US) (2022 - 2023)
- San Francisco, CA (US) (2015 - 2024)
- Monte Rio, CA (US) (2024)
Company Filing History:
Years Active: 2015-2024
Title: Thomas Edward Bagby: Innovator in Text-to-Speech Technology
Introduction
Thomas Edward Bagby is a prominent inventor based in San Francisco, CA. He has made significant contributions to the field of text-to-speech technology, holding a total of 9 patents. His innovative work focuses on creating systems and methods that enhance the capabilities of text-to-speech applications.
Latest Patents
Among his latest patents is a groundbreaking neural-network-based text-to-speech model for novel speaker generation. This invention allows systems to obtain text data and output audio data, incorporating speaker preferences that include various speaker characteristics. The technology processes these preferences through a machine-learned model to generate audio data that reflects the text spoken by a novel speaker. Another notable patent is related to variational embedding capacity in expressive end-to-end speech synthesis. This method estimates embedding capacity by analyzing reconstruction loss in relation to embedding dimensionality, ultimately improving the quality of synthesized speech.
Career Highlights
Thomas Edward Bagby is currently employed at Google Inc., where he continues to push the boundaries of speech synthesis technology. His work has been instrumental in advancing the capabilities of artificial intelligence in understanding and generating human-like speech.
Collaborations
Throughout his career, Bagby has collaborated with talented individuals such as Russell John Wyatt Skerry-Ryan and Eric Dean Battenberg. These collaborations have fostered an environment of innovation and creativity, leading to the development of cutting-edge technologies.
Conclusion
Thomas Edward Bagby is a key figure in the field of text-to-speech technology, with a strong portfolio of patents that reflect his innovative spirit. His contributions continue to shape the future of artificial intelligence and speech synthesis.