Jonathan Raiman

Title: Innovations of Jonathan Raiman

Introduction

Jonathan Raiman is an accomplished inventor based in Palo Alto, CA (US). He has made significant contributions to the field of text-to-speech technology, holding a total of 6 patents. His work focuses on enhancing the quality and efficiency of neural text-to-speech systems.

Latest Patents

One of his latest patents is for a real-time neural text-to-speech system. This system is constructed from deep neural networks and comprises five major building blocks: 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 with Connectionist Temporal Classification (CTC) loss for phoneme boundary detection. Additionally, a variant of WaveNet was created for the audio synthesis model, which requires fewer parameters and trains faster than the original. This innovative approach allows for faster-than-real-time inference and simplifies the traditional TTS system architecture.

Another notable patent is for a multi-speaker neural text-to-speech system. This system augments neural speech synthesis networks with low-dimensional trainable speaker embeddings, enabling the generation of speech from different voices using a single model. Improved single-speaker model embodiments, referred to as Deep Voice 2, were developed alongside a post-processing neural vocoder for Tacotron. These advancements demonstrate that neural text-to-speech systems can learn hundreds of unique voices from just twenty-five minutes of audio per speaker.

Career Highlights

Jonathan Raiman is currently employed at Baidu USA LLC, where he continues to push the boundaries of speech synthesis technology. His innovative work has positioned him as a key figure in the development of advanced TTS systems.

Collaborations

He collaborates with talented individuals such as John Miller and Sercan Omer Arik, contributing to the advancement of their shared goals in the field of speech technology.

Conclusion

Jonathan Raiman's contributions to neural text-to-speech technology are noteworthy and impactful. His innovative patents and work at Baidu USA LLC highlight his dedication to enhancing communication through advanced technology.