Company Filing History:
Years Active: 2025
Title: Innovations in Speech Synthesis by Sharath Keshava Narayana
Introduction
Sharath Keshava Narayana is an accomplished inventor based in Palo Alto, CA. He has made significant contributions to the field of speech synthesis, particularly through his innovative patent that utilizes neural networks for style extraction in speech processing.
Latest Patents
Sharath holds a patent titled "System and method for style extraction in speech synthesis using neural networks and stored augmentations to simulate degraded speech characteristics." This technology encompasses methods, speech processing systems, and non-transitory computer-readable media designed for style extraction in speech synthesis. The patent outlines a process where content and non-content elements are extracted from input audio data. A trained autoencoder encodes the input pitch into a low-dimensional vector, which is then used to generate a new representation of the input speech. The resulting output audio data provides a pitch-consistent reconstruction of the original speech.
Career Highlights
Sharath is currently employed at Sanas.ai Inc., where he continues to develop cutting-edge technologies in speech synthesis. His work focuses on enhancing the quality and realism of synthesized speech, making it more relatable and natural for users.
Collaborations
Sharath collaborates with talented individuals such as Lukas Pfeifenberger and Shawn Zhang, contributing to a dynamic team environment that fosters innovation and creativity.
Conclusion
Sharath Keshava Narayana's contributions to speech synthesis through his innovative patent demonstrate his expertise and commitment to advancing technology in this field. His work at Sanas.ai Inc. continues to push the boundaries of what is possible in speech processing.