Browsing by Author "Zhang, Chunlei"
Now showing 1 - 2 of 2
- Results Per Page
- Sort Options
Item Deep Neural Network Based Speaker Verification Under Domain Mismatched Conditions(2019-05) Zhang, Chunlei; 0000-0002-3851-2357 (Zhang, C); Hansen, John H.L.Speaker verification (SV), which offers a natural and flexible solution for biometric authentication, has been actively studied in the past decades. Machine learning models usually achieve high performance with the independent and identically distributed (I.I.D.) train/test set assumption, however their performance degrades dramatically when tested with none I.I.D. samples. In the research of speaker detection/verificaftion, this is called domain mismatch. Although recent advancements have greatly improved the reliability of SV systems, they are still prone to performance degradation under many domain mismatched conditions. Generally, domain mismatch can be categorized into two classes: (i) the intrinsic-speaker mismatch, which is the variability being introduced by the changes within a speaker her/himself (e.g., duration, stress, emotion and age etc.); (ii) the extrinsic-speaker mismatch, which is usually carried by external environmental factors, such as noise or channel distortions. In this dissertation, we aim to develop SV systems which are robust against domain mismatch. In the first part of this dissertation, novel i-vector and deep neural network (DNN) based non-neutral speech detection systems are investigated. As the preprocessing for actual SV systems, this portion of study aims to know when the SV systems are at risk, which in turn can improve the robustness of SV systems. Specifically, for non-neutral speech detection (i.e., physical stress detection and spoofing detection in this dissertation), different benchmarks such as the i-vector systems or several deep learning architectures have been examined, a novel system which simultaneously employs Convolutional Neural network (CNN) and Recurrent Neural Network (RNN) is proposed. Features including previously formulated Teager Energy Operator Critical Band Autocorrelation Envelope (TEO-CB-Auto-Env), Perceptual Minimum Variance Distortionless Response (PMVDR) and a more general spectrogram are also incorporated as the input to the proposed frameworks. Experiments on non-neutral speech copora show that the proposed methods achieve improved system performance. In the second part of this dissertation, we focus on the development of novel speaker embedding systems for SV tasks. We propose a novel text-independent SV framework based on the triplet loss and a deep CNN architecture, where a fixed-dimension embedding is extracted as an alternative speaker representation to replace the previous dominated i-vector model. On various standard SV copora with intrinsic-speaker or extrinsic-speaker domain mismatch, our proposed approaches achieve significant performance improvements over traditional frameworks. Lastly, transfer learning based domain adaptation methods are employed to further improve the performance of the triplet loss based speaker embedding system on UTScopePhysical corpus. Overall, the proposed individual components result in strong systems for DNN based speaker verification.Item Niclosamide Ethanolamine Improves Diabetes and Diabetic Kidney Disease in Mice(e-Century Publishing Corporation) Han, Pengxun; Shao, Mumin; Guo, Lan; Wang, Wenjing; Song, Gaofeng; Yu, Xuewen; Zhang, Chunlei; Ge, Na; Yi, Tiegang; Li, Shunmin; Du, Heng; Sun, Huili; Guo, Lan; Du, HengDiabetes and its renal complications are major medical challenges worldwide. There are no effective drugs currently available for treating diabetes and diabetic kidney disease (DKD), especially in type 1 diabetes (T1D). Evidence has suggested that niclosamide ethanolamine salt (NEN) could improve diabetic symptoms in mice of type 2 diabetes (T2D). However, its role in T1D and DKD has not been studied to date. Here we report that NEN could protect against diabetes in streptozotocin (STZ) induced T1D mice. It increased serum insulin levels, corrected the unbalanced ratio of alpha-cells to beta-cells, and induced islet morphologic changes under diabetic conditions. In addition, NEN could impede the progression of DKD in T1D. Specifically, it reduced urinary albumin levels, NAG, NGAL and TGF-beta 1 excretion, ameliorated renal hypertrophy, alleviated podocyte dysfunction, and suppressed the renal cortical activation of mTOR/4E-BP1 signaling pathway. Moreover, it is hepatoprotective and does not exhibit heart toxicity. Therefore, these findings open up a completely novel therapy for diabetes and DKD.