477 citations · 680 across the 10 of their papers we have counts for
10 papers
Streaming Target-Speaker ASR with Neural Transducer
Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai +2
Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-…
Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction
Yidong Wang, Hao Wu, Ao Liu +6
Target-oriented Opinion Words Extraction (TOWE) is a fine-grained sentiment analysis task that aims to extract the corresponding opinion words of a given opinion target from the se…
USB: A Unified Semi-supervised Learning Benchmark for Classification
Yidong Wang, Hao Chen, Yue Fan +19
Semi-supervised learning (SSL) improves model generalization by leveraging massive unlabeled data to augment limited labeled samples. However, currently, popular SSL evaluation pro…
Censer: Curriculum Semi-supervised Learning for Speech Recognition Based on Self-supervised Pre-training
Bowen Zhang, Songjun Cao, Xiaoming Zhang +3
Recent studies have shown that the benefits provided by self-supervised pre-training and self-training (pseudo-labeling) are complementary. Semi-supervised fine-tuning strategies u…
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Yidong Wang, Hao Chen, Qiang Heng +9
Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization.…
Margin Calibration for Long-Tailed Visual Recognition
Yidong Wang, Bowen Zhang, Wenxin Hou +3
The long-tailed class distribution in visual recognition tasks poses great challenges for neural networks on how to handle the biased predictions between head and tail classes, i.e…
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
Bowen Zhang, Yidong Wang, Wenxin Hou +4
The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a pre-d…
Exploiting Adapters for Cross-lingual Low-resource Speech Recognition
Wenxin Hou, Han Zhu, Yidong Wang +4
Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource…
Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching
Wenxin Hou, Jindong Wang, Xu Tan +2
End-to-end automatic speech recognition (ASR) can achieve promising performance with large-scale training data. However, it is known that domain mismatch between training and testi…
Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection
Taku Kato, Takahiro Shinozaki
Speech recognition systems have achieved high recognition performance for several tasks. However, the performance of such systems is dependent on the tremendously costly developmen…