57 Result(s)
-
Article
Edge-aware texture filtering with superpixels constraint
Extracting meaningful structural edges from complex texture images presents a significant challenge. Accurately measuring and differentiating texture information within an image are crucial for efficient textu...
-
Chapter and Conference Paper
Adaptive Deep Graph Convolutional Network for Dialogical Speech Emotion Recognition
With the increasing demand for humanization of human-computer interaction, dialogical speech emotion recognition (SER) has attracted the attention from researchers, and it is more aligned with actual scenarios...
-
Chapter and Conference Paper
Task-Adaptive Generative Adversarial Network Based Speech Dereverberation for Robust Speech Recognition
Reverberation is known to severely affect speech recognition performance when speech is recorded in an enclosed space. Deep learning-based speech dereverberation has been remarkably successful in recent years,...
-
Article
A fusion machine approach for pulse train deinterleaving
For the classification of radar emitters, it is important to be able to separate pulses in the interleaved pulse train in terms of their source. In practical scenarios, the received pulse train may miss a numb...
-
Chapter and Conference Paper
An Improved Stimulus Reconstruction Method for EEG-Based Short-Time Auditory Attention Detection
Short-time auditory attention detection (AAD) based on electroencephalography (EEG) can be utilized to help hearing-impaired people improve their perception abilities in multi-speaker environments. However, th...
-
Chapter and Conference Paper
Spoof Speech Detection Based on Raw Cross-Dimension Interaction Attention Network
Benefiting from advances in speech synthesis and speech conversion technology, artificial speech is so close to natural speech that it is sensory indistinguishable. This situation brings great challenges to th...
-
Chapter and Conference Paper
Application of CG Pseudo-spectral Method to Optimal Posture Adjustment of Robot Manipulator
To consider the energy saving during the robot motion, optimal posture control method for a robot manipulator is proposed. The Chebyshev-Gauss (CG) Pseudo-spectral method is used to discuss the problem with th...
-
Chapter and Conference Paper
Exploring Effective Speech Representation via ASR for High-Quality End-to-End Multispeaker TTS
The quality of multispeaker text-to-speech (TTS) is composed of speech naturalness and speaker similarity. The current multispeaker TTS based on speaker embeddings extracted by speaker verification (SV) or spe...
-
Chapter and Conference Paper
Quality-Aware Memory Network for Interactive Volumetric Image Segmentation
Despite recent progress of automatic medical image segmentation techniques, fully automatic results usually fail to meet the clinical use and typically require further refinement. In this work, we propose a quali...
-
Chapter and Conference Paper
A Sentiment Similarity-Oriented Attention Model with Multi-task Learning for Text-Based Emotion Recognition
Emotion recognition based on text modality has been one of the major topics in the field of emotion recognition in conversation. How to extract efficient emotional features is still a challenge. Previous studi...
-
Article
Occluded offline handwritten Chinese character recognition using deep convolutional generative adversarial network and improved GoogLeNet
In this paper, we propose a novel method for recognizing occluded offline handwritten Chinese characters based on deep convolutional generative adversarial network (DCGAN) and improved GoogLeNet. Different fro...
-
Chapter and Conference Paper
Speaker-Aware Speech Emotion Recognition by Fusing Amplitude and Phase Information
The use of a convolutional neural network (CNN) for extracting deep acoustic features from spectrograms has become one of the most commonly used methods for speech emotion recognition. In those studies, howeve...
-
Chapter and Conference Paper
Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection
Most existing AU detection works considering AU relationships are relying on probabilistic graphical models with manually extracted features. This paper proposes an end-to-end deep learning framework for facia...
-
Article
Removing ring artifacts in CBCT images via generative adversarial networks with unidirectional relative total variation loss
Cone beam computed tomography (CBCT) is an important tool for clinical diagnosis and many industrial applications. However, ring artifacts usually appear in CBCT images, due to device responding inconsistence...
-
Chapter and Conference Paper
Small Object Detection on Road by Embedding Focal-Area Loss
In recent years, with the continuous popularity of deep learning, the research on artificial intelligence has boosted the progress of many new applications, such as the autonomous driving. At present, the dete...
-
Chapter and Conference Paper
Time-Frequency Deep Representation Learning for Speech Emotion Recognition Integrating Self-attention
Learning efficient deep representations from spectrogram for speech emotion recognition still represents a significant challenge. Most existing spectrogram feature extraction methods empowered by deep learning...
-
Chapter and Conference Paper
The Method of Urban Intelligent Address Coding Based on Spatiotemporal Semantics
With the development of science and technology and the progress of society, urban construction in China is also develo** rapidly. Intelligent address coding plays an important role in urban planning and des...
-
Chapter and Conference Paper
A Fast Convolutional Self-attention Based Speech Dereverberation Method for Robust Speech Recognition
Speech dereverberation based on deep learning has recently gained a remarkable success with the substantial improvement of speech recognition for the accuracy in the distant speech recognition task. However, e...
-
Chapter and Conference Paper
A Testbed for Service Testing: A Cloud Computing Based Approach
Although simulation is an important tool in studying new emerged networks, tests on a real system are still the most ultimate way to validate the capability of a newly emerged network. Traditional tests have t...
-
Chapter and Conference Paper
Robust Sound Event Classification with Local Time-Frequency Information and Convolutional Neural Networks
How to effectively and accurately identify the sound event in a real-world noisy environment is still a challenging problem. Traditional methods for robust sound event classification generally perform well in ...
