This inventor holds 1 USPTO granted patent. Top assignee: Naver Corporation. Active years: 2025.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2025
Title: Inyoung Kim: Innovator in Neural Text-to-Speech Technology
Introduction
Inyoung Kim is a prominent inventor based in Meylan, France. She has made significant contributions to the field of artificial intelligence, particularly in the development of neural text-to-speech (TTS) models. Her innovative work focuses on enhancing the naturalness and expressiveness of synthesized speech.
Latest Patents
Inyoung Kim holds 1 patent for her invention titled "End-to-end neural text-to-speech model with prosody control." This patent describes methods and systems for generating an end-to-end neural TTS model that processes input text to produce speech representations. The model utilizes an annotated set of text documents, which include annotations indicating prosodic features. By training the TTS model with this annotated dataset and a corresponding dataset of speech representations, the model learns to associate prosody with the annotations, resulting in more natural-sounding speech.
Career Highlights
Inyoung Kim is currently employed at Naver Corporation, where she continues to push the boundaries of TTS technology. Her work has garnered attention for its potential applications in various industries, including virtual assistants, audiobooks, and accessibility tools.
Collaborations
Throughout her career, Inyoung has collaborated with notable colleagues, including Laurent Besacier and Siddique Latif. These partnerships have contributed to the advancement of her research and the successful development of her innovative technologies.
Conclusion
Inyoung Kim is a trailblazer in the field of neural text-to-speech technology, with her groundbreaking patent showcasing her expertise and dedication to innovation. Her contributions are paving the way for more natural and expressive speech synthesis in various applications.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
