Company Filing History:
Years Active: 2025
Title: Lev Finkelstein: Innovator in Speech Technology
Introduction
Lev Finkelstein is a prominent inventor based in Mountain View, CA. He has made significant contributions to the field of speech technology, holding 2 patents that showcase his innovative approaches to text-to-speech systems.
Latest Patents
Finkelstein's latest patents include groundbreaking methods for enhancing speech synthesis. One of his patents, titled "Two-level speech prosody transfer," involves a method that receives an input text utterance to be synthesized into expressive speech with intended prosody and a target voice. This method generates an intermediate synthesized speech representation using a first text-to-speech (TTS) model, which possesses the intended prosody. The intermediate representation is then processed by a second TTS model to produce an output audio signal that reflects the desired characteristics.
Another notable patent is "Two-level text-to-speech systems using synthetic training data." This method involves obtaining training data that includes various audio signals and transcripts. It generates training synthesized speech representations in different accents or dialects, allowing for the synthesis of speech that clones the voice of a target speaker in a specified accent or dialect.
Career Highlights
Lev Finkelstein is currently employed at Google Inc., where he continues to push the boundaries of speech technology. His work focuses on developing advanced TTS systems that enhance user experience through expressive and natural-sounding speech synthesis.
Collaborations
Finkelstein collaborates with talented individuals in his field, including Chun-an Chan and Byungha Chun. These collaborations contribute to the innovative projects he undertakes at Google Inc.
Conclusion
Lev Finkelstein is a key figure in the advancement of speech technology, with his patents reflecting a commitment to improving text-to-speech systems. His work continues to influence the way we interact with technology through voice.