Xiang Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiang Xie has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Jing Wang
Beijing Institute of Technology
5 shared publications - Chenguang Hu
School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China
3 shared publications - Fengrun Zhang
Beijing Institute of Technology
2 shared publications - Huachun Tan
Beijing Institute of Technology
2 shared publications Jingming Kuang
School of Information Science and Technology, Beijing Institute of Technology, Beijing 100081, China
2 shared publications- Jingming Kuang
Beijing Institute of Technology
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (22) , 54821-54833
Multientity Time Series Forecasting in IoT Systems via Regime and Entity Conditioning
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (22) , 54821-54833
Multientity Time Series Forecasting in IoT Systems via Regime and Entity Conditioning
- 2 January 2026
- Published by Springer Nature
- p. 470-481
A Timbre Attribute Discrimination System Fusing Pre-trained Speaker Feature Extractors with Gender Prior Features
- 2 January 2026
- Published by Springer Nature
- p. 470-481
A Timbre Attribute Discrimination System Fusing Pre-trained Speaker Feature Extractors with Gender Prior Features
- Open Access
- 29 January 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (3) , 1097
College Students’ Views on Museum Learning: A Sustainable Aesthetic Education Perspective
Museums are important educational platforms in informal learning environments, offering essential off-campus venues for university-level aesthetic education. Over half of students’ independent off-campus art appreciation activities occur in museums. This study employed a mixed-methods approach to analyse students’ general impressions of museums using the TF-IDF algorithm. Additionally, the specific feelings of university students participating in self-directed museum learning were explored through focus groups, and differences between learning in museums and appreciating other art forms from the students’ perspectives were analysed. The results show that museums provide students with profound cultural and artistic knowledge. Students prefer museums for independent art appreciation because of the freedom, control, and safety offered in that learning process. In terms of interactivity, comprehensiveness, and repeatability, clear differences exist between museum art appreciation and other art disciplines. Overall, museums are important and sustainable off-campus aesthetic educational resources for universities.
- 29 January 2025
- Published by MDPI AG in Sustainability
- Vol. 17 (3) , 1097
Open AccessCollege Students’ Views on Museum Learning: A Sustainable Aesthetic Education Perspective
Museums are important educational platforms in informal learning environments, offering essential off-campus venues for university-level aesthetic education. Over half of students’ independent off-campus art appreciation activities occur in museums. This study employed a mixed-methods approach to analyse students’ general impressions of museums using the TF-IDF algorithm. Additionally, the specific feelings of university students participating in self-directed museum learning were explored through focus groups, and differences between learning in museums and appreciating other art forms from the students’ perspectives were analysed. The results show that museums provide students with profound cultural and artistic knowledge. Students prefer museums for independent art appreciation because of the freedom, control, and safety offered in that learning process. In terms of interactivity, comprehensiveness, and repeatability, clear differences exist between museum art appreciation and other art disciplines. Overall, museums are important and sustainable off-campus aesthetic educational resources for universities.
- 5 December 2024
- Published by Springer Nature
- p. 343-355
ASD-Diffusion: Anomalous Sound Detection with Diffusion Models
- 5 December 2024
- Published by Springer Nature
- p. 343-355
ASD-Diffusion: Anomalous Sound Detection with Diffusion Models
- 1 December 2024
- Published by Springer Nature
- p. 141-153
Semi-supervised Cross-Lingual Speech Recognition Exploiting Articulatory Features
- 1 December 2024
- Published by Springer Nature
- p. 141-153
Semi-supervised Cross-Lingual Speech Recognition Exploiting Articulatory Features
- Open Access
ASD-Diffusion: Anomalous Sound Detection with Diffusion Models
Unsupervised Anomalous Sound Detection (ASD) aims to design a generalizable method that can be used to detect anomalies when only normal sounds are given. In this paper, Anomalous Sound Detection based on Diffusion Models (ASD-Diffusion) is proposed for ASD in real-world factories. In our pipeline, the anomalies in acoustic features are reconstructed from their noisy corrupted features into their approximate normal pattern. Secondly, a post-processing anomalies filter algorithm is proposed to detect anomalies that exhibit significant deviation from the original input after reconstruction. Furthermore, denoising diffusion implicit model is introduced to accelerate the inference speed by a longer sampling interval of the denoising process. The proposed method is innovative in the application of diffusion models as a new scheme. Experimental results on the development set of DCASE 2023 challenge task 2 outperform the baseline by 7.75%, demonstrating the effectiveness of the proposed method.
Open AccessASD-Diffusion: Anomalous Sound Detection with Diffusion Models
Unsupervised Anomalous Sound Detection (ASD) aims to design a generalizable method that can be used to detect anomalies when only normal sounds are given. In this paper, Anomalous Sound Detection based on Diffusion Models (ASD-Diffusion) is proposed for ASD in real-world factories. In our pipeline, the anomalies in acoustic features are reconstructed from their noisy corrupted features into their approximate normal pattern. Secondly, a post-processing anomalies filter algorithm is proposed to detect anomalies that exhibit significant deviation from the original input after reconstruction. Furthermore, denoising diffusion implicit model is introduced to accelerate the inference speed by a longer sampling interval of the denoising process. The proposed method is innovative in the application of diffusion models as a new scheme. Experimental results on the development set of DCASE 2023 challenge task 2 outperform the baseline by 7.75%, demonstrating the effectiveness of the proposed method.
- Open Access
- 5 January 2024
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 6, 1104064
Sentiment interpretability analysis on Chinese texts employing multi-task and knowledge base
With the rapid development of deep learning techniques, the applications have become increasingly widespread in various domains. However, traditional deep learning methods are often referred to as “black box” models with low interpretability of their results, posing challenges for their application in certain critical domains. In this study, we propose a comprehensive method for the interpretability analysis of sentiment models. The proposed method encompasses two main aspects: attention-based analysis and external knowledge integration. First, we train the model within sentiment classification and generation tasks to capture attention scores from multiple perspectives. This multi-angle approach reduces bias and provides a more comprehensive understanding of the underlying sentiment. Second, we incorporate an external knowledge base to improve evidence extraction. By leveraging character scores, we retrieve complete sentiment evidence phrases, addressing the challenge of incomplete evidence extraction in Chinese texts. Experimental results on a sentiment interpretability evaluation dataset demonstrate the effectiveness of our method. We observe a notable increase in accuracy by 1.3%, Macro-F1 by 13%, and MAP by 23%. Overall, our approach offers a robust solution for enhancing the interpretability of sentiment models by combining attention-based analysis and the integration of external knowledge.
- 5 January 2024
- Published by Frontiers Media SA in Frontiers in Artificial Intelligence
- Vol. 6, 1104064
Open AccessSentiment interpretability analysis on Chinese texts employing multi-task and knowledge base
With the rapid development of deep learning techniques, the applications have become increasingly widespread in various domains. However, traditional deep learning methods are often referred to as “black box” models with low interpretability of their results, posing challenges for their application in certain critical domains. In this study, we propose a comprehensive method for the interpretability analysis of sentiment models. The proposed method encompasses two main aspects: attention-based analysis and external knowledge integration. First, we train the model within sentiment classification and generation tasks to capture attention scores from multiple perspectives. This multi-angle approach reduces bias and provides a more comprehensive understanding of the underlying sentiment. Second, we incorporate an external knowledge base to improve evidence extraction. By leveraging character scores, we retrieve complete sentiment evidence phrases, addressing the challenge of incomplete evidence extraction in Chinese texts. Experimental results on a sentiment interpretability evaluation dataset demonstrate the effectiveness of our method. We observe a notable increase in accuracy by 1.3%, Macro-F1 by 13%, and MAP by 23%. Overall, our approach offers a robust solution for enhancing the interpretability of sentiment models by combining attention-based analysis and the integration of external knowledge.
- Open Access
Multi-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy
In advanced transportation-management systems, variable speed limits are a crucial application. Deep reinforcement learning methods have been shown to have superior performance in many applications, as they are an effective approach to learning environment dynamics for decision-making and control. However, they face two significant difficulties in traffic-control applications: reward engineering with delayed reward and brittle convergence properties with gradient descent. To address these challenges, evolutionary strategies are well suited as a class of black-box optimization techniques inspired by natural evolution. Additionally, the traditional deep reinforcement learning framework struggles to handle the delayed reward setting. This paper proposes a novel approach using covariance matrix adaptation evolution strategy (CMA-ES), a gradient-free global optimization method, to handle the task of multi-lane differential variable speed limit control. The proposed method uses a deep-learning-based method to dynamically learn optimal and distinct speed limits among lanes. The parameters of the neural network are sampled using a multivariate normal distribution, and the dependencies between the variables are represented by a covariance matrix that is optimized dynamically by CMA-ES based on the freeway’s throughput. The proposed approach is tested on a freeway with simulated recurrent bottlenecks, and the experimental results show that it outperforms deep reinforcement learning-based approaches, traditional evolutionary search methods, and the no-control scenario. Our proposed method demonstrates a 23% improvement in average travel time and an average of a 4% improvement in CO, HC, and NOx emission.Furthermore, the proposed method produces explainable speed limits and has desirable generalization power.
Open AccessMulti-Lane Differential Variable Speed Limit Control via Deep Neural Networks Optimized by an Adaptive Evolutionary Strategy
In advanced transportation-management systems, variable speed limits are a crucial application. Deep reinforcement learning methods have been shown to have superior performance in many applications, as they are an effective approach to learning environment dynamics for decision-making and control. However, they face two significant difficulties in traffic-control applications: reward engineering with delayed reward and brittle convergence properties with gradient descent. To address these challenges, evolutionary strategies are well suited as a class of black-box optimization techniques inspired by natural evolution. Additionally, the traditional deep reinforcement learning framework struggles to handle the delayed reward setting. This paper proposes a novel approach using covariance matrix adaptation evolution strategy (CMA-ES), a gradient-free global optimization method, to handle the task of multi-lane differential variable speed limit control. The proposed method uses a deep-learning-based method to dynamically learn optimal and distinct speed limits among lanes. The parameters of the neural network are sampled using a multivariate normal distribution, and the dependencies between the variables are represented by a covariance matrix that is optimized dynamically by CMA-ES based on the freeway’s throughput. The proposed approach is tested on a freeway with simulated recurrent bottlenecks, and the experimental results show that it outperforms deep reinforcement learning-based approaches, traditional evolutionary search methods, and the no-control scenario. Our proposed method demonstrates a 23% improvement in average travel time and an average of a 4% improvement in CO, HC, and NOx emission.Furthermore, the proposed method produces explainable speed limits and has desirable generalization power.
- Open Access
- 20 December 2021
- Published by MDPI AG in Electronics
- Vol. 10 (24) , 3172
Domain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition
Phonological-based features (articulatory features, AFs) describe the movements of the vocal organ which are shared across languages. This paper investigates a domain-adversarial neural network (DANN) to extract reliable AFs, and different multi-stream techniques are used for cross-lingual speech recognition. First, a novel universal phonological attributes definition is proposed for Mandarin, English, German and French. Then a DANN-based AFs detector is trained using source languages (English, German and French). When doing the cross-lingual speech recognition, the AFs detectors are used to transfer the phonological knowledge from source languages (English, German and French) to the target language (Mandarin). Two multi-stream approaches are introduced to fuse the acoustic features and cross-lingual AFs. In addition, the monolingual AFs system (i.e., the AFs are directly extracted from the target language) is also investigated. Experiments show that the performance of the AFs detector can be improved by using convolutional neural networks (CNN) with a domain-adversarial learning method. The multi-head attention (MHA) based multi-stream can reach the best performance compared to the baseline, cross-lingual adaptation approach, and other approaches. More specifically, the MHA-mode with cross-lingual AFs yields significant improvements over monolingual AFs with the restriction of training data size and, which can be easily extended to other low-resource languages.
- 20 December 2021
- Published by MDPI AG in Electronics
- Vol. 10 (24) , 3172
Open AccessDomain-Adversarial Based Model with Phonological Knowledge for Cross-Lingual Speech Recognition
Phonological-based features (articulatory features, AFs) describe the movements of the vocal organ which are shared across languages. This paper investigates a domain-adversarial neural network (DANN) to extract reliable AFs, and different multi-stream techniques are used for cross-lingual speech recognition. First, a novel universal phonological attributes definition is proposed for Mandarin, English, German and French. Then a DANN-based AFs detector is trained using source languages (English, German and French). When doing the cross-lingual speech recognition, the AFs detectors are used to transfer the phonological knowledge from source languages (English, German and French) to the target language (Mandarin). Two multi-stream approaches are introduced to fuse the acoustic features and cross-lingual AFs. In addition, the monolingual AFs system (i.e., the AFs are directly extracted from the target language) is also investigated. Experiments show that the performance of the AFs detector can be improved by using convolutional neural networks (CNN) with a domain-adversarial learning method. The multi-head attention (MHA) based multi-stream can reach the best performance compared to the baseline, cross-lingual adaptation approach, and other approaches. More specifically, the MHA-mode with cross-lingual AFs yields significant improvements over monolingual AFs with the restriction of training data size and, which can be easily extended to other low-resource languages.
- Open Access
- 14 September 2021
- Published by MDPI AG in Electronics
- Vol. 10 (18) , 2259
A Self-Supervised Model for Language Identification Integrating Phonological Knowledge
In this paper, a self-supervised learning pre-trained model is proposed and successfully applied in language identification task (LID). A Transformer encoder is employed and multi-task strategy is used to train the self-supervised model: the first task is to reconstruct the masking spans of input frames and the second task is a supervision task where the phoneme and phonological labels are used with Connectionist Temporal Classification (CTC) loss. By using this multi-task learning loss, the model is expected to capture high-level speech representation in phonological space. Meanwhile, an adaptive loss is also applied for multi-task learning to balance the weight between different tasks. After the pretraining stage, the self-supervised model is used for xvector systems. Our LID experiments are carried out on the oriental language recognition (OLR) challenge data corpus and 1 s, 3 s, Full-length test sets are selected. Experimental results show that on 1 s test set, feature extraction model approach can get best performance and in 3 s, Full-length test, the fine-tuning approach can reach the best performance. Furthermore, our results prove that the multi-task training strategy is effective and the proposed model can get the best performance.
- 14 September 2021
- Published by MDPI AG in Electronics
- Vol. 10 (18) , 2259
Open AccessA Self-Supervised Model for Language Identification Integrating Phonological Knowledge
In this paper, a self-supervised learning pre-trained model is proposed and successfully applied in language identification task (LID). A Transformer encoder is employed and multi-task strategy is used to train the self-supervised model: the first task is to reconstruct the masking spans of input frames and the second task is a supervision task where the phoneme and phonological labels are used with Connectionist Temporal Classification (CTC) loss. By using this multi-task learning loss, the model is expected to capture high-level speech representation in phonological space. Meanwhile, an adaptive loss is also applied for multi-task learning to balance the weight between different tasks. After the pretraining stage, the self-supervised model is used for xvector systems. Our LID experiments are carried out on the oriental language recognition (OLR) challenge data corpus and 1 s, 3 s, Full-length test sets are selected. Experimental results show that on 1 s test set, feature extraction model approach can get best performance and in 3 s, Full-length test, the fine-tuning approach can reach the best performance. Furthermore, our results prove that the multi-task training strategy is effective and the proposed model can get the best performance.