49 citations · 158 across the 25 of their papers we have counts for
25 papers
Triplet Knowledge Distillation
Xijun Wang, Dongyang Liu, Meina Kan +3
In Knowledge Distillation, the teacher is generally much larger than the student, making the solution of the teacher likely to be difficult for the student to learn. To ease the mi…
FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition
Xingchen Song, Di Wu, Binbin Zhang +8
The recently proposed Conformer architecture which combines convolution with attention to capture both local and global dependencies has become the \textit{de facto} backbone model…
A Character-level Span-based Model for Mandarin Prosodic Structure Prediction
Xueyuan Chen, Changhe Song, Yixuan Zhou +4
The accuracy of prosodic structure prediction is crucial to the naturalness of synthesized speech in Mandarin text-to-speech system, but now is limited by widely-used sequence-to-s…
Syntax-Aware Network for Handwritten Mathematical Expression Recognition
Ye Yuan, Xiao Liu, Wondimu Dikubab +4
Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance wit…
BERT-LID: Leveraging BERT to Improve Spoken Language Identification
Yuting Nie, Junhong Zhao, Wei-Qiang Zhang +1
Language identification is the task of automatically determining the identity of a language conveyed by a spoken segment. It has a profound impact on the multilingual interoperabil…
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
Yuxiang Wei, Yupeng Shi, Xiao Liu +4
Unsupervised disentanglement learning is a crucial issue for understanding and exploiting deep generative models. Recently, SeFa tries to find latent disentangled directions by per…
UniCon: Unified Context Network for Robust Active Speaker Detection
Yuanhang Zhang, Susan Liang, Shuang Yang +4
We introduce a new efficient framework, the Unified Context Network (UniCon), for robust active speaker detection (ASD). Traditional methods for ASD usually operate on each candida…
Structured Multi-modal Feature Embedding and Alignment for Image-Sentence Retrieval
Xuri Ge, Fuhai Chen, Joemon M. Jose +3
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modu…
Locality-aware Channel-wise Dropout for Occluded Face Recognition
Mingjie He, Jie Zhang, Shiguang Shan +3
Face recognition remains a challenging task in unconstrained scenarios, especially when faces are partially occluded. To improve the robustness against occlusion, augmenting the tr…
Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension
Shiting Xu, Guowei Xu, Peilei Jia +3
Task requirements (TRs) writing is an important question type in Key English Test and Preliminary English Test. A TR writing question may include multiple requirements and a high-q…
A Multimodal Machine Learning Framework for Teacher Vocal Delivery Evaluation
Hang Li, Yu Kang, Yang Hao +3
The quality of vocal delivery is one of the key indicators for evaluating teacher enthusiasm, which has been widely accepted to be connected to the overall course qualities. Howeve…
Solving ESL Sentence Completion Questions via Pre-trained Neural Language Models
Qiongqiong Liu, Tianqiao Liu, Jiafu Zhao +6
Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options. SC questions are widely…
Multi-Task Learning based Online Dialogic Instruction Detection with Pre-trained Language Models
Yang Hao, Hang Li, Wenbiao Ding +4
In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective st…
Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Mining
Guowei Xu, Wenbiao Ding, Weiping Fu +2
Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Pr…
Towards the Memorization Effect of Neural Networks in Adversarial Training
Han Xu, Xiaorui Liu, Wentao Wang +5
Recent studies suggest that ``memorization'' is one important factor for overparameterized deep neural networks (DNNs) to achieve optimal performance. Specifically, the perfectly f…
Multi-Scale Attention Neural Network for Acoustic Echo Cancellation
Lu Ma, Song Yang, Yaguang Gong +1
Acoustic Echo Cancellation (AEC) plays a key role in speech interaction by suppressing the echo received at microphone introduced by acoustic reverberations from loudspeakers. Sinc…
Noise Classification Aided Attention-Based Neural Network for Monaural Speech Enhancement
Lu Ma, Song Yang, Yaguang Gong +1
This paper proposes an noise type classification aided attention-based neural network approach for monaural speech enhancement. The network is constructed based on a previous work…
Multi-Scale Temporal Convolution Network for Classroom Voice Detection
Lu Ma, Xintian Wang, Song Yang +2
Teaching with the cooperation of expert teacher and assistant teacher, which is the so-called "double-teachers classroom", i.e., the course is giving by the expert online and prese…
EchoFilter: End-to-End Neural Network for Acoustic Echo Cancellation
Lu Ma, Song Yang, Yaguang Gong +2
Acoustic Echo Cancellation (AEC) whose aim is to suppress the echo originated from acoustic coupling between loudspeakers and microphones, plays a key role in voice interaction. Li…
Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
Yue Cao, Xiaohe Wu, Shuran Qi +3
The success of deep denoisers on real-world color photographs usually relies on the modeling of sensor noise and in-camera signal processing (ISP) pipeline. Performance drop will i…
AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text
Zhihong Shao, Zitao Liu, Jiyong Zhang +2
Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some cha…
Personalized Multimodal Feedback Generation in Education
Haochen Liu, Zitao Liu, Zhongqin Wu +1
The automatic evaluation for school assignments is an important application of AI in the education field. In this work, we focus on the task of personalized multimodal feedback gen…
Learning Fine-Grained Cross Modality Excitement for Speech Emotion Recognition
Hang Li, Wenbiao Ding, Zhongqin Wu +1
Speech emotion recognition is a challenging task because the emotion expression is complex, multimodal and fine-grained. In this paper, we propose a novel multimodal deep learning…
Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations
Tianqiao Liu, Qiang Fang, Wenbiao Ding +3
There is an increasing interest in the use of mathematical word problem (MWP) generation in educational assessment. Different from standard natural question generation, MWP generat…