Mike Chrzanowski

Title: Mike Chrzanowski: Innovator in Neural Text-to-Speech Technology

Introduction

Mike Chrzanowski is a prominent inventor based in Sunnyvale, CA (US). He has made significant contributions to the field of text-to-speech (TTS) technology, particularly through his work with deep neural networks. With a total of 4 patents, Chrzanowski is recognized for his innovative approaches to enhancing the quality and efficiency of TTS systems.

Latest Patents

Chrzanowski's latest patents focus on real-time neural text-to-speech systems. These embodiments describe a production-quality TTS system constructed from deep neural networks, comprising five major building blocks. These include a segmentation model for locating phoneme boundaries, a grapheme-to-phoneme conversion model, a phoneme duration prediction model, a fundamental frequency prediction model, and an audio synthesis model. The segmentation model utilizes deep neural networks for phoneme boundary detection, employing Connectionist Temporal Classification (CTC) loss. Additionally, a variant of WaveNet was developed for the audio synthesis model, which requires fewer parameters and trains faster than the original. This innovative approach allows for simpler and more flexible system embodiments compared to traditional TTS systems, which often require extensive feature engineering and domain expertise. Inference with these systems can be performed faster than real time.

Career Highlights

Chrzanowski is currently employed at Baidu USA LLC, where he continues to push the boundaries of TTS technology. His work has garnered attention for its potential to revolutionize how machines understand and generate human speech.

Collaborations

Some of his notable coworkers include Bryan Catanzaro and Jingdong Chen, who have also contributed to advancements in artificial intelligence and machine learning.

Conclusion

Mike Chrzanowski stands out as an influential inventor in the realm of neural text-to-speech technology. His innovative patents and contributions to the field are paving the way for more advanced and efficient communication systems.