Location History:
- San Jose, CA (US) (2017)
- Redwood City, CA (US) (2022 - 2024)
Company Filing History:
Years Active: 2017-2024
Title: Soroosh Mariooryad: Innovator in Text-to-Speech Technology
Introduction
Soroosh Mariooryad is a prominent inventor based in Redwood City, CA. He has made significant contributions to the field of text-to-speech technology, holding a total of 6 patents. His work focuses on developing advanced systems that enhance the capabilities of speech synthesis.
Latest Patents
One of his latest patents is titled "Neural-network-based text-to-speech model for novel speaker generation." This innovative system allows for the generation of audio data from text input, incorporating speaker preferences that include various characteristics. The technology utilizes a machine-learned model to create a speaker embedding, which is then processed with the text data to produce audio that mimics a novel speaker. Another notable patent is "Variational embedding capacity in expressive end-to-end speech synthesis." This method involves estimating an embedding capacity by analyzing reference audio signals and their corresponding embeddings. It measures reconstruction losses to compare the performance of different embeddings, ultimately enhancing the efficiency of speech synthesis.
Career Highlights
Soroosh Mariooryad is currently employed at Google Inc., where he continues to push the boundaries of speech technology. His work at Google has allowed him to collaborate with some of the brightest minds in the industry, contributing to groundbreaking advancements in artificial intelligence and machine learning.
Collaborations
Some of his notable coworkers include Eric Dean Battenberg and Daisy Stanton. Their collaborative efforts have further enriched the innovative environment at Google, leading to the development of cutting-edge technologies in speech synthesis.
Conclusion
Soroosh Mariooryad is a key figure in the advancement of text-to-speech technology, with a focus on creating systems that enhance user experience through innovative methods. His contributions are shaping the future of how machines understand and generate human speech.