Baidu USA LLC

Shubhahrata Sengupta

Sercan Omer Arik

Gregory Diamos

Adam Coates

John Miller

Jonathan Raiman

Andrew Gibiansky

Mike Chrzanowski

Andrew Ng

Mohammad Shoeybi

Embodiments of a production-quality text-to-speech (TTS) system constructed from deep neural networks are described. System embodiments comprise 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. For embodiments of the segmentation model, phoneme boundary detection was performed with deep neural networks using Connectionist Temporal Classification (CTC) loss. For embodiments of the audio synthesis model, a variant of WaveNet was created that requires fewer parameters and trains faster than the original. By using a neural network for each component, system embodiments are simpler and more flexible than traditional TTS systems, where each component requires laborious feature engineering and extensive domain expertise. Inference with system embodiments may be performed faster than real time.

Real-time neural text-to-speech

Systems and methods for real-time neural text-to-speech

Growing community of inventors

Menlo Park, CA, United States of America

Shubhahrata Sengupta