Zhao Lv
YOU?
Author Swipe
View article: Dyadic Neural Synchronization: Differences between Offline and Computer‐assisted Online Verbal Interaction
Dyadic Neural Synchronization: Differences between Offline and Computer‐assisted Online Verbal Interaction Open
Computer‐assisted online interaction (CAOI) has become predominant in daily life and is increasingly supplanting offline verbal interaction (FVI). Previous research has shown that face‐to‐face verbal interaction (VI) exhibits significant d…
View article: IEFS-GMB: Gradient Memory Bank-Guided Feature Selection Based on Information Entropy for EEG Classification of Neurological Disorders
IEFS-GMB: Gradient Memory Bank-Guided Feature Selection Based on Information Entropy for EEG Classification of Neurological Disorders Open
Deep learning-based EEG classification is crucial for the automated detection of neurological disorders, improving diagnostic accuracy and enabling early intervention. However, the low signal-to-noise ratio of EEG signals limits model perf…
View article: M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction
M3ANet: Multi-scale and Multi-Modal Alignment Network for Brain-Assisted Target Speaker Extraction Open
The brain-assisted target speaker extraction (TSE) aims to extract the attended speech from mixed speech by utilizing the brain neural activities, for example Electroencephalography (EEG). However, existing models overlook the issue of tem…
View article: BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement
BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement Open
Although the complex spectrum-based speech enhancement (SE) methods have achieved significant performance, coupling amplitude and phase can lead to a compensation effect, where amplitude information is sacrificed to compensate for the phas…
View article: Region-Based Optimization in Continual Learning for Audio Deepfake Detection
Region-Based Optimization in Continual Learning for Audio Deepfake Detection Open
Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes…
View article: How do the resting EEG preprocessing states affect the outcomes of postprocessing?
How do the resting EEG preprocessing states affect the outcomes of postprocessing? Open
Plenty of artifact removal tools and pipelines have been developed to correct the resting EEG waves and discover scientific values behind. Without expertised visual inspection, it is susceptible to derive improper preprocessing, resulting …
View article: SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG
SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG Open
Decoding speech from brain signals is a challenging research problem that holds significant importance for studying speech processing in the brain. Although breakthroughs have been made in reconstructing the mel spectrograms of audio stimu…
View article: STMTNet: Spatio-Temporal Multiscale Triad Network for Cropland Change Detection in Remote Sensing Images
STMTNet: Spatio-Temporal Multiscale Triad Network for Cropland Change Detection in Remote Sensing Images Open
Cropland change detection in remote sensing is hindered by spatial heterogeneity and temporal noise, leading to misaligned representations and erroneous change identification. We propose the spatio-temporal multiscale triad network (STMTNe…
View article: BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement
BSDB-Net: Band-Split Dual-Branch Network with Selective State Spaces Mechanism for Monaural Speech Enhancement Open
Although the complex spectrum-based speech enhancement(SE) methods have achieved significant performance, coupling amplitude and phase can lead to a compensation effect, where amplitude information is sacrificed to compensate for the phase…
View article: Region-Based Optimization in Continual Learning for Audio Deepfake Detection
Region-Based Optimization in Continual Learning for Audio Deepfake Detection Open
Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes…
View article: Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective
Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective Open
The robustness of Graph Neural Networks (GNNs) has become an increasingly important topic due to their expanding range of applications. Various attack methods have been proposed to explore the vulnerabilities of GNNs, ranging from Graph Mo…
View article: UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models
UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Models Open
Sequential decision-making refers to algorithms that take into account the dynamics of the environment, where early decisions affect subsequent decisions. With large language models (LLMs) demonstrating powerful capabilities between tasks,…
View article: Frequency-mix Knowledge Distillation for Fake Speech Detection
Frequency-mix Knowledge Distillation for Fake Speech Detection Open
In the telephony scenarios, the fake speech detection (FSD) task to combat speech spoofing attacks is challenging. Data augmentation (DA) methods are considered effective means to address the FSD task in telephony scenarios, typically divi…
View article: Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion Open
In recent years, knowledge graph completion (KGC) models based on pre-trained language model (PLM) have shown promising results. However, the large number of parameters and high computational cost of PLM models pose challenges for their ap…
View article: Effects of diesel injection timing and methanol substitution ratio on combustion and exhaust emission characteristics of a dual fuel compression ignition engine
Effects of diesel injection timing and methanol substitution ratio on combustion and exhaust emission characteristics of a dual fuel compression ignition engine Open
Based on a diesel-methanol dual-fuel engine, the effects of diesel injection timing and methanol substitution ratio on the combustion, emissions and fuel economy of dual-fuel engines at different loads were investigated. The results showed…
View article: A Two-Stage Stacked Transformer Framework for Multimodal Sentiment Analysis
A Two-Stage Stacked Transformer Framework for Multimodal Sentiment Analysis Open
Transformer-based methods have achieved superior performance in multimodal sentiment analysis (MSA). However, recent studies have used it more to focus on the potential mutual adaptation between unimodal modalities, while ignoring intra-mo…
View article: How do the resting EEG preprocessing states affect the outcomes of postprocessing?
How do the resting EEG preprocessing states affect the outcomes of postprocessing? Open
Plenty of artifact removal tools and pipelines have been developed to correct the EEG recordings and discover the values below the waveforms. Without visual inspection from the experts, it is susceptible to derive improper preprocessing st…
View article: Spectral homogeneity cross frequencies can be a quality metric for the large-scale resting EEG preprocessing
Spectral homogeneity cross frequencies can be a quality metric for the large-scale resting EEG preprocessing Open
The brain projects require the collection of massive electrophysiological data, aiming to the longitudinal, sectional, or populational neuroscience studies. Quality metrics automatically label the data after centralized preprocessing. Howe…
View article: DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention Detection
DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention Detection Open
Auditory Attention Detection (AAD) aims to detect target speaker from brain signals in a multi-speaker environment. Although EEG-based AAD methods have shown promising results in recent years, current approaches primarily rely on tradition…
View article: Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection
Spatial Reconstructed Local Attention Res2Net with F0 Subband for Fake Speech Detection Open
The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discri…
View article: Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection
Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection Open
In this paper, we propose the multi-perspective information fusion (MPIF) Res2Net with random Specmix for fake speech detection (FSD). The main purpose of this system is to improve the model's ability to learn precise forgery information f…
View article: Learning From Yourself: A Self-Distillation Method for Fake Speech Detection
Learning From Yourself: A Self-Distillation Method for Fake Speech Detection Open
In this paper, we propose a novel self-distillation method for fake speech detection (FSD), which can significantly improve the performance of FSD without increasing the model complexity. For FSD, some fine-grained information is very impo…
View article: Predicting Moral Elevation Conveyed in Danmaku Comments Using EEGs
Predicting Moral Elevation Conveyed in Danmaku Comments Using EEGs Open
Moral elevation, the emotion that arises when individuals observe others’ moral behaviors, plays an important role in determining moral behaviors in real life. While recent research has demonstrated the potential to decode basic emotions w…
View article: An Investigation of Olfactory-Enhanced Video on EEG-Based Emotion Recognition
An Investigation of Olfactory-Enhanced Video on EEG-Based Emotion Recognition Open
Collecting emotional physiological signals is significant in building affective Human-Computer Interactions (HCI). However, how to evoke subjects' emotions efficiently in EEG-related emotional experiments is still a challenge. In this work…
View article: Similarity Function for One-Shot Learning to Enhance the Flexibility of Myoelectric Interfaces
Similarity Function for One-Shot Learning to Enhance the Flexibility of Myoelectric Interfaces Open
$\textit {Objective:}$ This study aims to develop a flexible myoelectric pattern recognition (MPR) method based on one-shot learning, which enables convenient switching across different usage scenarios, thereby reducing the re-training bur…