no code implementations • 19 Jul 2023 • Jiahao Xun, Shengyu Zhang, Yanting Yang, Jieming Zhu, Liqun Deng, Zhou Zhao, Zhenhua Dong, RuiQi Li, Lichao Zhang, Fei Wu
We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning.
no code implementations • 12 Apr 2022 • Daxin Tan, Liqun Deng, Nianzu Zheng, Yu Ting Yeung, Xin Jiang, Xiao Chen, Tan Lee
This study propose a fully automated system for speech correction and accent reduction.
no code implementations • 28 Jan 2022 • Shuai Zhang, Jiangyan Yi, Zhengkun Tian, JianHua Tao, Yu Ting Yeung, Liqun Deng
We propose a language-related attention mechanism to reduce multilingual context confusion for the E2E code-switching ASR model based on the Equivalence Constraint (EC) Theory.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
no code implementations • 16 Nov 2021 • Nianzu Zheng, Liqun Deng, Wenyong Huang, Yu Ting Yeung, Baohua Xu, Yuanyuan Guo, Yasheng Wang, Xiao Chen, Xin Jiang, Qun Liu
We utilize conv-transformer structure to encode input speech in a streaming manner.
1 code implementation • 4 Jul 2021 • Daxin Tan, Liqun Deng, Yu Ting Yeung, Xin Jiang, Xiao Chen, Tan Lee
This paper presents the design, implementation and evaluation of a speech editing system, named EditSpeech, which allows a user to perform deletion, insertion and replacement of words in a given speech utterance, without causing audible degradation in speech quality and naturalness.
1 code implementation • 18 Jun 2021 • Disong Wang, Liqun Deng, Yu Ting Yeung, Xiao Chen, Xunying Liu, Helen Meng
One-shot voice conversion (VC), which performs conversion across arbitrary speakers with only a single target-speaker utterance for reference, can be effectively achieved by speech representation disentanglement.
no code implementations • 18 Jun 2021 • Disong Wang, Liqun Deng, Yu Ting Yeung, Xiao Chen, Xunying Liu, Helen Meng
Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target domains respectively, but the two domains may differ in terms of speech stimuli, disease etiology, etc.
no code implementations • 31 Dec 2020 • Yang Zhang, Liqun Deng, Yasheng Wang
The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.