no code implementations • 17 Oct 2023 • Jie Pu, Thai-Son Nguyen, Sebastian Stüker
In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems.
no code implementations • 7 Feb 2022 • Jie Pu, Yixiong Meng, Oguz Elibol
The diversity of speaker profiles in multi-speaker TTS systems is a crucial aspect of its performance, as it measures how many different speaker profiles TTS systems could possibly synthesize.