no code implementations • 8 Jan 2024 • Yusheng Tian, Jingyu Li, Tan Lee
Experimental results on a real case of tongue cancer patient confirm that the synthetic voice achieves comparable articulation quality to unimpaired natural speech, while effectively maintaining the target speaker's individuality.
no code implementations • 27 May 2023 • Yusheng Tian, Guangyan Zhang, Tan Lee
Specifically, a diffusion-based speech synthesis model is trained on original recordings, to capture and preserve the target speaker's original articulation style.
1 code implementation • 18 May 2023 • Yusheng Tian, Wei Liu, Tan Lee
One way to address this problem is to pre-enhance the speech with an enhancement model and then use the enhanced data for text-to-speech (TTS) model training.
no code implementations • 31 Oct 2022 • Jingyu Li, Yusheng Tian, Tan Lee
The weights are imposed on the input features to improve the representation ability for speaker modeling.
no code implementations • 26 Jun 2022 • Yusheng Tian, Jingyu Li, Tan Lee
Pooling is needed to aggregate frame-level features into utterance-level representations for speaker modeling.
no code implementations • 15 Jun 2022 • Jingyu Li, Yusheng Tian, Tan Lee
There is no reason to expect that these features are optimal for all different tasks, including speaker verification (SV).
no code implementations • 5 Aug 2020 • Yusheng Tian, Philip John Gorinski
In this paper, we suggest improving the generalization performance of SLU models with a non-standard learning algorithm, Reptile.
Ranked #12 on Spoken Language Understanding on Fluent Speech Commands (using extra training data)