1 code implementation • 18 Dec 2023 • Rui Cao, Tianrui Wang, Meng Ge, Longbiao Wang, Jianwu Dang
By bridging the speech enhancement and the Information Bottleneck principle in this letter, we rethink a universal plug-and-play strategy and propose a Refining Underlying Information framework called RUI to rise to the challenges both in theory and practice.
no code implementations • 8 Jul 2023 • Jian Wu, Yashesh Gaur, Zhuo Chen, Long Zhou, Yimeng Zhu, Tianrui Wang, Jinyu Li, Shujie Liu, Bo Ren, Linquan Liu, Yu Wu
Large language models (LLMs) have achieved remarkable success in the field of natural language processing, enabling better human-computer interaction using natural language.
no code implementations • 25 May 2023 • Tianrui Wang, Long Zhou, Ziqiang Zhang, Yu Wu, Shujie Liu, Yashesh Gaur, Zhuo Chen, Jinyu Li, Furu Wei
Recent research shows a big convergence in model architecture, training objectives, and inference methods across various tasks for different modalities.
no code implementations • 11 Nov 2022 • Tianrui Wang, Xie Chen, Zhuo Chen, Shu Yu, Weibin Zhu
In recent years, self-supervised learning (SSL) has achieved tremendous success in various speech tasks due to its power to extract representations from massive unlabeled data.
no code implementations • 16 Jun 2022 • Yingying Gao, Junlan Feng, Tianrui Wang, Chao Deng, Shilei Zhang
Analysis shows that our proposed approach brings a better uniformity for the trained model and enlarges the CTC spikes obviously.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 1 Apr 2022 • Tianrui Wang, Weibin Zhu, Yingying Gao, Junlan Feng, Shilei Zhang
Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments.
no code implementations • 25 Feb 2022 • Tianrui Wang, Weibin Zhu, Yingying Gao, Yanan Chen, Junlan Feng, Shilei Zhang
Therefore, we previously proposed a harmonic gated compensation network (HGCN) to predict the full harmonic locations based on the unmasked harmonics and process the result of a coarse enhancement module to recover the masked harmonics.
1 code implementation • 30 Jan 2022 • Tianrui Wang, Weibin Zhu, Yingying Gao, Junlan Feng, Shilei Zhang
Mask processing in the time-frequency (T-F) domain through the neural network has been one of the mainstreams for single-channel speech enhancement.
1 code implementation • 26 Aug 2021 • Tianrui Wang, Weibin Zhu
Deep learning technology has been widely applied to speech enhancement.
no code implementations • 17 Oct 2020 • Dan Wang, Tianrui Wang, Ionuţ Florescu
We find that using imaging techniques to input data for CNN works better for financial ratio data but is not significantly better than simply using the 1D input directly for fundamental data.