Rohan Badlani

Title: Innovations by Rohan Badlani in Text-to-Speech Synthesis

Introduction

Rohan Badlani is an accomplished inventor based in San Jose, California. He has made significant contributions to the field of text-to-speech synthesis, particularly through his innovative use of neural networks. With a total of two patents to his name, Badlani is recognized for his advancements in generating synthetic speech.

Latest Patents

Rohan Badlani's latest patents focus on "Unsupervised alignment for text to speech synthesis using neural networks." This invention addresses the challenges of generating synthetic speech from input text sequences when the durations of individual phonemes are unknown. The predominantly parallel process he developed models speech rhythm as a separate generative distribution, allowing phoneme duration to be sampled during inference. Additionally, the invention incorporates sampling of other information, such as pitch or energy, to enhance the diversity of synthetic speech generation.

Career Highlights

Rohan Badlani is currently employed at Nvidia Corporation, a leading technology company known for its advancements in graphics processing and artificial intelligence. His work at Nvidia has allowed him to explore and implement cutting-edge technologies in the realm of speech synthesis.

Collaborations

Some of Rohan Badlani's notable coworkers include Kevin Shih and Jose Rafael Valle Gomes Da Costa. Their collaboration has likely contributed to the innovative projects and research initiatives at Nvidia Corporation.

Conclusion

Rohan Badlani's contributions to text-to-speech synthesis through his patents and work at Nvidia Corporation highlight his role as a significant inventor in the field. His innovative approaches continue to push the boundaries of synthetic speech technology.