Tieran Zheng

Tieran Zheng


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 August 2012 in IEEE Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
ZSZiqiang Shi
Ziqiang Shi
JHJiqing Han
Jiqing Han
TZTieran Zheng
Tieran Zheng
SDShiwen Deng
Shiwen Deng
In order to naturally combine audio information from different dimensions and build robust audio processing system, a novel framework based on low-rank tensor representation features for audio segment classification is proposed in this paper. The audio signal is first transformed into tensor format data, and then these tensor data are mapped to a low-rank space which is insensitive under certain noises, especially white Gaussian noise and gross corruptions. For these low-rank tensor based features, tensor classification via a linear classifier based on minimization a smooth loss function regularized by the trace norm proposed recently is used. Most previous methods find the weight tensor and bias in batch-mode learning, which makes them inefficient for large-scale problems. In this paper, we propose to address this problem with an online learning algorithm based on the accelerated proximal gradient (APG) method, which scales up gracefully to large data sets. Experiments on simulation and real audio data demonstrate the efficiency of the methods.

29 August 2024 in IEEE/ACM Transactions on Audio, Speech, and Language Processing
Verified
Journal Article
Closed access
YGYadong Guan
Yadong Guan
JHJiqing Han
Jiqing Han
HSHongwei Song
Hongwei Song
SDShi-wen Deng
Shi-wen Deng
GZGuibin Zheng
Guibin Zheng
YHYongjun He
Yongjun He
The training of sound event detection (SED) models remains a challenge of insufficient supervision due to limited frame-wise labeled data. Mainstream research on this problem has adopted semi-supervised training strategies that generate pseudo-labels for unlabeled data and use these data for the training of a model. Recent works further introduce multi-task training strategies to impose additional supervision. However, the auxiliary tasks employed in these methods either lack frame-wise guidance or exhibit unsuitable task designs. Furthermore, they fail to exploit inter-task relationships effectively, which can serve as valuable supervision. In this paper, we introduce a novel task, sound occurrence and overlap detection (SOD), which detects predefined sound activity patterns, including non-overlapping and overlapping cases. On the basis of SOD, we propose a cross-task collaborative training framework that leverages the relationship between SED and SOD to improve the SED model. Firstly, by jointly optimizing the two tasks in a multi-task manner, the SED model is encouraged to learn features sensitive to sound activity. Subsequently, the cross-task consistency regularization is proposed to promote consistent predictions between SED and SOD. Finally, we propose a pseudo-label selection method that uses inconsistent predictions between the two tasks to identify potential wrong pseudo-labels and mitigate their confirmation bias. In the inference phase, only the trained SED model is used, thus no additional computation and storage costs are incurred. Extensive experiments on the DESED dataset demonstrate the effectiveness of our method.

18 February 2014 in Circuits, Systems, and Signal Processing
Verified
Journal Article
Closed access
PDF file
DYDatao You
Datao You
JHJiqing Han
Jiqing Han
GZGuibin Zheng
Guibin Zheng
TZTieran Zheng
Tieran Zheng
JLJie Li
Jie Li

15 October 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
WSWenjie Song
Wenjie Song
JHJiqing Han
Jiqing Han
SDShi-wen Deng
Shi-wen Deng
TZTieran Zheng
Tieran Zheng
GZGuibin Zheng
Guibin Zheng
YHYongjun He
Yongjun He
Semi-supervised learning effectively mitigates the lack of labeled data by introducing extensive unlabeled data. Despite achieving success in respiratory sound classification, in practice, it usually takes years to acquire a sufficiently sizeable unlabeled set, which consequently results in an extension of the research timeline. Considering that there are also respiratory sounds available in other related tasks, like breath phase detection and COVID-19 detection, it might be an alternative manner to treat these external samples as unlabeled data for respiratory sound classification. However, since these external samples are collected in different scenarios via different devices, there inevitably exists a distribution mismatch between the labeled and external unlabeled data. For existing methods, they usually assume that the labeled and unlabeled data follow the same data distribution. Therefore, they cannot benefit from external samples. To utilize external unlabeled data, we propose a semi-supervised method based on Joint Energy-based Model (JEM) in this paper. During training, the method attempts to use only the essential semantic components within the samples to model the data distribution. When non-semantic components like recording environments and devices vary, as these non-semantic components have a small impact on the model training, a relatively accurate distribution estimation is obtained. Therefore, the method exhibits insensitivity to the distribution mismatch, enabling the model to leverage external unlabeled data to mitigate the lack of labeled data. Taking ICBHI 2017 as the labeled set, HF_Lung_V1 and COVID-19 Sounds as the external unlabeled sets, the proposed method exceeds the baseline by 12.86.

1 August 2016 in IOP Conference Series: Earth and Environmental Science
Verified
Conference Paper
Open access
PDF file
Tao RenTao Ren
Tao Ren
XGX R Gao
X R Gao
TZTieran Zheng
Tieran Zheng
Pan WangPan Wang
Pan Wang
There are problems with treating acidic waste water containing high concentration fluorine by chemical precipitation, including the low sludge setting velocity and the high difficulty of reaching the criterion. In Heilongjiang province, a graphite factory producing high-purity graphite generates acidic waste water with a high concentration of fluorine. In this paper, the effect of removals on the concentration of fluoride with the combined treatment of calcium oxide and calcium chloride were discussed with regard to acid waste water. The study improved the sludge characteristics by using polyacrylamide (PAM) and polymeric aluminum chloride (PAC). The effect of different coagulants on sludge was evaluated by the sludge settlement ratio (SV), sludge volume index (SVI) and sludge moisture content. The results showed that the optimal combination for 100 ml waste water was calcium oxide addition amount of 14 g, a calcium chloride addition amount of 2.5 g, a PAM addition amount of 350 mg/L, and the effluent fluoride concentration was below 6 mg/L. PAM significantly improved the sludge settling velocity. The sludge settlement ratio reduced from 87.6% to 60%. The process for wastewater treatment was easily operated and involved low expenditure.

1 January 2012 in International Journal of Computer and Electrical Engineering
Verified
Journal Article
Closed access
ZSZiqiang Shi
Ziqiang Shi
TZTieran Zheng
Tieran Zheng
JHJiqing Han
Jiqing Han
BGBoyang Gao
Boyang Gao