Company Filing History:
Years Active: 2020-2023
Title: Innovations by Andrew Gibiansky in Neural Text-to-Speech Technology
Introduction
Andrew Gibiansky is an accomplished inventor based in Mountain View, CA (US). He has made significant contributions to the field of neural text-to-speech (TTS) systems, holding a total of 6 patents. His work focuses on enhancing the quality and efficiency of speech synthesis through innovative technologies.
Latest Patents
Gibiansky's latest patents include groundbreaking advancements in real-time neural text-to-speech systems. One of his notable inventions is a production-quality TTS system constructed from deep neural networks. This system 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, the audio synthesis model is a variant of WaveNet that requires fewer parameters and trains faster than the original. This innovative approach allows for faster-than-real-time inference, making the system simpler and more flexible than traditional TTS systems.
Another significant patent involves multi-speaker neural text-to-speech technology. This invention describes systems and methods for augmenting neural speech synthesis networks with low-dimensional trainable speaker embeddings. This allows for 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
Andrew Gibiansky is currently employed at Baidu USA LLC, where he continues to push the boundaries of speech synthesis technology. His work has garnered attention for its innovative approach and practical applications in various fields.
Collaborations
Gibiansky collaborates with talented individuals such as Sercan Omer Arik and Jonathan Raiman, contributing to the advancement of neural TTS systems.
Conclusion
Andrew Gibiansky's contributions to neural text-to-speech technology exemplify the power of innovation in enhancing communication systems. His patents reflect a commitment to improving the efficiency and quality of speech synthesis, paving the way for future advancements in this field
Inventor’s Patent Attorneys refers to legal professionals with specialized expertise in representing inventors throughout the patent process. These attorneys assist inventors in navigating the complexities of patent law, including filing patent applications, conducting patent searches, and protecting intellectual property rights. They play a crucial role in helping inventors secure patents for their innovative creations.