Elluru Veera Raghavendra

Title: Innovations of Elluru Veera Raghavendra in F0 Transfer Learning

Introduction

Elluru Veera Raghavendra is a notable inventor based in Hyderabad, Telangana, India. He has made significant contributions to the field of deep learning, particularly in the area of speech synthesis. His innovative work focuses on improving fundamental frequency (F0) prediction using advanced neural network models.

Latest Patents

Raghavendra holds a patent titled "System and method for F0 transfer learning for improving F0 prediction with deep neural network models." This patent presents a system and method that utilizes long short-term memory (LSTM) and multi-layer perceptron (MLP) feed-forward hidden layer modeling. The invention identifies and extracts fundamental frequency values for both voiced and unvoiced segments from larger models. The values for voiced regions are then transferred to train a smaller model, which is subsequently applied in a text-to-speech system for real-time speech synthesis output. He has 1 patent to his name.

Career Highlights

Raghavendra's career is marked by his dedication to advancing technology in speech synthesis. His work has implications for various applications, including voice assistants and automated speech systems. His innovative approach to F0 prediction has garnered attention in the research community.

Collaborations

Raghavendra collaborates with Aravind Ganapathiraju, contributing to the development of cutting-edge technologies in their field. Their partnership enhances the potential for further advancements in deep learning applications.

Conclusion

Elluru Veera Raghavendra's contributions to F0 transfer learning and deep neural networks highlight his role as an influential inventor in the field of speech synthesis. His innovative patent demonstrates the potential for real-time applications in technology.