Xionghu Zhong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Xionghu Zhong has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Jielong Yang
School of Internet of Things Engineering, Jiangnan University, Wuxi, China
7 shared publications - Eng Siong Chng
Nanyang Technological University (NTU)
4 shared publications - Minjie Cai
College of Computer Science and Electronic Engineering, Hunan University, Changsha, China
3 shared publications - A. Benjamin Premkumar
School of Computer Engineering, College of Engineering, Nanyang Technological University, Singapore
2 shared publications - Chongxiao Wang
Institute of High Performance Computing, Agency for Science, Technology and Research
2 shared publications - Hao Chen
College of Computer Science and Electronic Engineering, Hunan University, Changsha, China
2 shared publications
Latest Publications
- 1 August 2026
- Published by Springer Nature
- p. 301-316
TextBFGS: A Case-Based Reasoning Approach to Code Optimization via Error-Operator Retrieval
- 1 August 2026
- Published by Springer Nature
- p. 301-316
TextBFGS: A Case-Based Reasoning Approach to Code Optimization via Error-Operator Retrieval
- 26 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-12
Machine Unlearning for Source-Free Unsupervised Partial-Domain Adaptation in Remote Sensing
Source-Free Unsupervised Domain Adaptation (SFUDA) enables model adaptation to unlabeled target domains without accessing source data. However, when the source domain contains classes absent in the target domain, existing methods suffer from negative transfer: knowledge of irrelevant source-only classes interferes with target class recognition, significantly degrading classification accuracy. We propose Machine Unlearning-based SFUDA (MUSFUDA), which addresses this problem by selectively unlearning source-only class knowledge from the pre-trained model rather than adding compensatory mechanisms. This machine unlearning approach allows the model to focus on shared classes, fundamentally eliminating negative transfer. Remote sensing images with large intra-class variations and high inter-class similarity cause over-unlearning of target classes when forgetting source-only classes, thus we design the Model-Disruption Based Dual-Teacher Unlearning Strategy (MDUS), which uses dual teachers to manage target class preservation and source-only class erasure through knowledge distillation. MDUS is lightweight and easily integrated into existing SFUDA frameworks. Experiments on remote sensing datasets demonstrate that combining MDUS with representative baselines consistently reduces negative transfer and improves classification performance, maintaining high efficiency, validating the effectiveness and generalizability of our approach.
- 26 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-12
Machine Unlearning for Source-Free Unsupervised Partial-Domain Adaptation in Remote Sensing
Source-Free Unsupervised Domain Adaptation (SFUDA) enables model adaptation to unlabeled target domains without accessing source data. However, when the source domain contains classes absent in the target domain, existing methods suffer from negative transfer: knowledge of irrelevant source-only classes interferes with target class recognition, significantly degrading classification accuracy. We propose Machine Unlearning-based SFUDA (MUSFUDA), which addresses this problem by selectively unlearning source-only class knowledge from the pre-trained model rather than adding compensatory mechanisms. This machine unlearning approach allows the model to focus on shared classes, fundamentally eliminating negative transfer. Remote sensing images with large intra-class variations and high inter-class similarity cause over-unlearning of target classes when forgetting source-only classes, thus we design the Model-Disruption Based Dual-Teacher Unlearning Strategy (MDUS), which uses dual teachers to manage target class preservation and source-only class erasure through knowledge distillation. MDUS is lightweight and easily integrated into existing SFUDA frameworks. Experiments on remote sensing datasets demonstrate that combining MDUS with representative baselines consistently reduces negative transfer and improves classification performance, maintaining high efficiency, validating the effectiveness and generalizability of our approach.
- Open Access
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-24
MatCo: Computing Match Cover of Subgraph Query over Graph Data
Subgraph query can be applied in various scenarios, such as fraud detection and cyberattack pattern analysis. However, computing subgraph queries usually traverses a huge search space. Many efforts have been made to reduce this search space. The size of the answer set can be exponential, providing a substantial lower bound for the search space. Additionally, different answers may overlap, and a single vertex can occur multiple times in different matches. In this paper, we propose a new problem to compute the match cover of a subgraph query. We define the match cover as a subset of answers such that the vertices included are exactly the same as those in the entire set. There can be more than one match covers, however, we only return one, as long as we can avoid the huge overhead of searching the entire set. It is inefficient to apply traditional subgraph query methods for computing match cover. Specifically, existing methods do not prune partial matches that could grow into full matches. For match cover computation, if the vertices in those full matches are already included in previously found matches, continuing the computation over such partial matches is a waste of time. We propose a new framework, called MatCo, to compute the match cover. In MatCo, we design a new data structure, called local candidate space, to determine whether the future search scopes of partial matches have been covered. We can easily maintain local candidate space and efficiently conduct the determination. We also reduce some Cartesian products, which are inevitable in existing methods, into linear enumerations, which significantly improves performance. Extensive experiments over various datasets confirm that our method outperforms comparative ones by 1~3 orders of magnitude. Efficiently computing the minimum match cover could be an interesting future work.
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-24
Open AccessMatCo: Computing Match Cover of Subgraph Query over Graph Data
Subgraph query can be applied in various scenarios, such as fraud detection and cyberattack pattern analysis. However, computing subgraph queries usually traverses a huge search space. Many efforts have been made to reduce this search space. The size of the answer set can be exponential, providing a substantial lower bound for the search space. Additionally, different answers may overlap, and a single vertex can occur multiple times in different matches. In this paper, we propose a new problem to compute the match cover of a subgraph query. We define the match cover as a subset of answers such that the vertices included are exactly the same as those in the entire set. There can be more than one match covers, however, we only return one, as long as we can avoid the huge overhead of searching the entire set. It is inefficient to apply traditional subgraph query methods for computing match cover. Specifically, existing methods do not prune partial matches that could grow into full matches. For match cover computation, if the vertices in those full matches are already included in previously found matches, continuing the computation over such partial matches is a waste of time. We propose a new framework, called MatCo, to compute the match cover. In MatCo, we design a new data structure, called local candidate space, to determine whether the future search scopes of partial matches have been covered. We can easily maintain local candidate space and efficiently conduct the determination. We also reduce some Cartesian products, which are inevitable in existing methods, into linear enumerations, which significantly improves performance. Extensive experiments over various datasets confirm that our method outperforms comparative ones by 1~3 orders of magnitude. Efficiently computing the minimum match cover could be an interesting future work.
- 21 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 2164-2168
UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation
Array-geometry-agnostic speech separation (AGA-SS) aims to develop an effective separation method regardless of the microphone array geometry. Conventional methods rely on permutation-free operations, such as summation or attention mechanisms, to capture spatial information. However, these approaches often incur high computational costs or disrupt the effective use of spatial information during intra- and inter-channel interactions, leading to suboptimal performance. To address these issues, we propose UniArray, a novel approach that abandons the conventional interleaving manner. UniArray consists of three key components: a virtual microphone estimation (VME) module, a feature extraction and fusion module, and a hierarchical dual-path separator. The VME ensures robust performance across arrays with varying channel numbers. The feature extraction and fusion module leverages a spectral feature extraction module and a spatial dictionary learning (SDL) module to extract and fuse frequency-bin-level features, allowing the separator to focus on using the fused features. The hierarchical dual-path separator models feature dependencies along the time and frequency axes while maintaining computational efficiency. Experimental results show that UniArray outperforms state-of-the-art methods in SI-SDRi, WB-PESQ, NB-PESQ, and STOI across both seen and unseen array geometries.
- 21 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 2164-2168
UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation
Array-geometry-agnostic speech separation (AGA-SS) aims to develop an effective separation method regardless of the microphone array geometry. Conventional methods rely on permutation-free operations, such as summation or attention mechanisms, to capture spatial information. However, these approaches often incur high computational costs or disrupt the effective use of spatial information during intra- and inter-channel interactions, leading to suboptimal performance. To address these issues, we propose UniArray, a novel approach that abandons the conventional interleaving manner. UniArray consists of three key components: a virtual microphone estimation (VME) module, a feature extraction and fusion module, and a hierarchical dual-path separator. The VME ensures robust performance across arrays with varying channel numbers. The feature extraction and fusion module leverages a spectral feature extraction module and a spatial dictionary learning (SDL) module to extract and fuse frequency-bin-level features, allowing the separator to focus on using the fused features. The hierarchical dual-path separator models feature dependencies along the time and frequency axes while maintaining computational efficiency. Experimental results show that UniArray outperforms state-of-the-art methods in SI-SDRi, WB-PESQ, NB-PESQ, and STOI across both seen and unseen array geometries.
- Open Access
UniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation
Array-geometry-agnostic speech separation (AGA-SS) aims to develop an effective separation method regardless of the microphone array geometry. Conventional methods rely on permutation-free operations, such as summation or attention mechanisms, to capture spatial information. However, these approaches often incur high computational costs or disrupt the effective use of spatial information during intra- and inter-channel interactions, leading to suboptimal performance. To address these issues, we propose UniArray, a novel approach that abandons the conventional interleaving manner. UniArray consists of three key components: a virtual microphone estimation (VME) module, a feature extraction and fusion module, and a hierarchical dual-path separator. The VME ensures robust performance across arrays with varying channel numbers. The feature extraction and fusion module leverages a spectral feature extraction module and a spatial dictionary learning (SDL) module to extract and fuse frequency-bin-level features, allowing the separator to focus on using the fused features. The hierarchical dual-path separator models feature dependencies along the time and frequency axes while maintaining computational efficiency. Experimental results show that UniArray outperforms state-of-the-art methods in SI-SDRi, WB-PESQ, NB-PESQ, and STOI across both seen and unseen array geometries.
Open AccessUniArray: Unified Spectral-Spatial Modeling for Array-Geometry-Agnostic Speech Separation
Array-geometry-agnostic speech separation (AGA-SS) aims to develop an effective separation method regardless of the microphone array geometry. Conventional methods rely on permutation-free operations, such as summation or attention mechanisms, to capture spatial information. However, these approaches often incur high computational costs or disrupt the effective use of spatial information during intra- and inter-channel interactions, leading to suboptimal performance. To address these issues, we propose UniArray, a novel approach that abandons the conventional interleaving manner. UniArray consists of three key components: a virtual microphone estimation (VME) module, a feature extraction and fusion module, and a hierarchical dual-path separator. The VME ensures robust performance across arrays with varying channel numbers. The feature extraction and fusion module leverages a spectral feature extraction module and a spatial dictionary learning (SDL) module to extract and fuse frequency-bin-level features, allowing the separator to focus on using the fused features. The hierarchical dual-path separator models feature dependencies along the time and frequency axes while maintaining computational efficiency. Experimental results show that UniArray outperforms state-of-the-art methods in SI-SDRi, WB-PESQ, NB-PESQ, and STOI across both seen and unseen array geometries.
- 24 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 1307-1323
Enhancing Overlapped Speech Detection and Speaker Counting With Spatially-Infused Spectro-Temporal Conformer
Overlapped speech is widely present in conversations and can cause significant performance degradation in speech processing such as diarization, enhancement, and recognition. Overlapped speech detection (OSD) and speaker counting, in particular when the speakers are in the far field, pose challenges as the overlapped part is usually short, and heavy reverberation and noise may present in the conversation scenario. Existing solutions predominantly rely on spectral features extracted from a single microphone signal to perform the detection. In this paper, we propose an innovative approach that is able to efficiently extract spatial features via spatial dictionary learning (SDL) and fuse spatial and spectral features derived from multi-channel array signals. In essence, a spectro-temporal module is employed to extract local information from the spectrogram which is able to better detect overlapping segments under real scenarios. Subsequently, we study two kinds of spatial features: directional statistics, which are projected onto spherical location grids using SDL, and generalized cross-correlation with phase transform (GCC-PHAT) to model the spatial characteristics of speakers. These spatial features are then integrated with the spectral features for the OSD and speaker counting. In addition, a non-parameter magnitude-weighted fusion method is employed to combine the magnitude spectrogram with SDL results, enabling the model to prioritize critical frequency bins. Finally, the performance of the proposed approach is studied under AMI, Alimeeting, and CHiME-6 corpora. Experimental results show that our proposed approach achieves better performance than methods using spectral features only. Furthermore, we also conduct experiments of speaker diarization with OSD to evaluate the detection performance.
- 24 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech and Language Processing
- Vol. 33, 1307-1323
Enhancing Overlapped Speech Detection and Speaker Counting With Spatially-Infused Spectro-Temporal Conformer
Overlapped speech is widely present in conversations and can cause significant performance degradation in speech processing such as diarization, enhancement, and recognition. Overlapped speech detection (OSD) and speaker counting, in particular when the speakers are in the far field, pose challenges as the overlapped part is usually short, and heavy reverberation and noise may present in the conversation scenario. Existing solutions predominantly rely on spectral features extracted from a single microphone signal to perform the detection. In this paper, we propose an innovative approach that is able to efficiently extract spatial features via spatial dictionary learning (SDL) and fuse spatial and spectral features derived from multi-channel array signals. In essence, a spectro-temporal module is employed to extract local information from the spectrogram which is able to better detect overlapping segments under real scenarios. Subsequently, we study two kinds of spatial features: directional statistics, which are projected onto spherical location grids using SDL, and generalized cross-correlation with phase transform (GCC-PHAT) to model the spatial characteristics of speakers. These spatial features are then integrated with the spectral features for the OSD and speaker counting. In addition, a non-parameter magnitude-weighted fusion method is employed to combine the magnitude spectrogram with SDL results, enabling the model to prioritize critical frequency bins. Finally, the performance of the proposed approach is studied under AMI, Alimeeting, and CHiME-6 corpora. Experimental results show that our proposed approach achieves better performance than methods using spectral features only. Furthermore, we also conduct experiments of speaker diarization with OSD to evaluate the detection performance.
- Open Access
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 181799-181807
Visible-Infrared Cross-Modality Person Re-Identification via Adaptive Weighted Triplet Loss and Progressive Training
Visible-infrared cross-modality person re-identification (VI-ReID) aims to search the same person images across multiple non-overlapping cameras of different modalities, which has a wider application scenario than single modality person re-identification task. The main difficulty of VI-ReID is the large visual difference between the visible and infrared modalities. In this paper, an adaptive weighted triplet loss is proposed, which can adaptively adjust the weights of triplet samples. This method can reduce the impact of outlier samples, and mainly focus on the major mid-hard samples. We also introduce a channel random shuffle data augmentation method. It can be easily integrated into the existing framework. This data augmentation method can reduce the dependence on color information, and improve the robustness against color variations. A progressive training strategy is employed, which can further improve the performance. Experiments show that our proposed methods achieve state-of-the-art results on two public datasets SYSU-MM01 and RegDB without additional computation.
- 2 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 181799-181807
Open AccessVisible-Infrared Cross-Modality Person Re-Identification via Adaptive Weighted Triplet Loss and Progressive Training
Visible-infrared cross-modality person re-identification (VI-ReID) aims to search the same person images across multiple non-overlapping cameras of different modalities, which has a wider application scenario than single modality person re-identification task. The main difficulty of VI-ReID is the large visual difference between the visible and infrared modalities. In this paper, an adaptive weighted triplet loss is proposed, which can adaptively adjust the weights of triplet samples. This method can reduce the impact of outlier samples, and mainly focus on the major mid-hard samples. We also introduce a channel random shuffle data augmentation method. It can be easily integrated into the existing framework. This data augmentation method can reduce the dependence on color information, and improve the robustness against color variations. A progressive training strategy is employed, which can further improve the performance. Experiments show that our proposed methods achieve state-of-the-art results on two public datasets SYSU-MM01 and RegDB without additional computation.
- 12 November 2024
- Published by Springer Nature
- p. 56-66
An Attention Model Based Approach for Leakage Detection in Water Distribution Networks Using Normal Pressure Data
- 12 November 2024
- Published by Springer Nature
- p. 56-66
An Attention Model Based Approach for Leakage Detection in Water Distribution Networks Using Normal Pressure Data
- Open Access
A Transformer-Based Approach to Leakage Detection in Water Distribution Networks
The efficient detection of leakages in water distribution networks (WDNs) is crucial to ensuring municipal water supply safety and improving urban operations. Traditionally, machine learning methods such as Convolutional Neural Networks (CNNs) and Autoencoders (AEs) have been used for leakage detection. However, these methods heavily rely on local pressure information and often fail to capture long-term dependencies in pressure series. In this paper, we propose a transformer-based model for detecting leakages in WDNs. The transformer incorporates an attention mechanism to learn data distributions and account for correlations between historical pressure data and data from the same time on different days, thereby emphasizing long-term dependencies in pressure series. Additionally, we apply pressure data normalization across each leakage scenario and concatenate position embeddings with pressure data in the transformer model to avoid feature misleading. The performance of the proposed method is evaluated by using detection accuracy and F1-score. The experimental studies conducted on simulated pressure datasets from three different WDNs demonstrate that the transformer-based model significantly outperforms traditional CNN methods.
Open AccessA Transformer-Based Approach to Leakage Detection in Water Distribution Networks
The efficient detection of leakages in water distribution networks (WDNs) is crucial to ensuring municipal water supply safety and improving urban operations. Traditionally, machine learning methods such as Convolutional Neural Networks (CNNs) and Autoencoders (AEs) have been used for leakage detection. However, these methods heavily rely on local pressure information and often fail to capture long-term dependencies in pressure series. In this paper, we propose a transformer-based model for detecting leakages in WDNs. The transformer incorporates an attention mechanism to learn data distributions and account for correlations between historical pressure data and data from the same time on different days, thereby emphasizing long-term dependencies in pressure series. Additionally, we apply pressure data normalization across each leakage scenario and concatenate position embeddings with pressure data in the transformer model to avoid feature misleading. The performance of the proposed method is evaluated by using detection accuracy and F1-score. The experimental studies conducted on simulated pressure datasets from three different WDNs demonstrate that the transformer-based model significantly outperforms traditional CNN methods.
- Open Access
Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs
The integration of large language models (LLMs) with pre-trained speech models has opened up new avenues in automatic speech recognition (ASR). While LLMs excel in multimodal understanding tasks, effectively leveraging their capabilities for ASR remains a significant challenge. This paper presents a novel training approach to enhance LLM performance in ASR tasks. We propose pre-training LLMs on Pinyin embedding sequences, which represent pronunciation features, to generate corresponding Chinese characters. This step enables the LLM to adapt to generating text from pronunciation features before encountering real speech data. Furthermore, we fine-tune the LoRA parameters to enhance the LLM's understanding of speech modality information. In AISHELL-1 corpus, our approach yields a 9.5% relative improvement in ASR tasks compared to the baseline without Pinyi-to-Character pre-training. Additionally, incorporating auxiliary text data for Pinyi-to-Character pre-training further boosts performance, achieving a 19.0% relative improvement.
Open AccessBridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs
The integration of large language models (LLMs) with pre-trained speech models has opened up new avenues in automatic speech recognition (ASR). While LLMs excel in multimodal understanding tasks, effectively leveraging their capabilities for ASR remains a significant challenge. This paper presents a novel training approach to enhance LLM performance in ASR tasks. We propose pre-training LLMs on Pinyin embedding sequences, which represent pronunciation features, to generate corresponding Chinese characters. This step enables the LLM to adapt to generating text from pronunciation features before encountering real speech data. Furthermore, we fine-tune the LoRA parameters to enhance the LLM's understanding of speech modality information. In AISHELL-1 corpus, our approach yields a 9.5% relative improvement in ASR tasks compared to the baseline without Pinyi-to-Character pre-training. Additionally, incorporating auxiliary text data for Pinyi-to-Character pre-training further boosts performance, achieving a 19.0% relative improvement.