Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- C-vector (1)
- Crystalline (1)
- Deep neural networks (1)
- I-vector (1)
- Latent class model (1)
-
- Look-up table (1)
- Motion control (1)
- Multi-task learning (1)
- NH4SCN (1)
- Perovskite solar cells (1)
- Phase error (1)
- Phase measuring profilometry (1)
- Phase unwrapping (1)
- Phonetic adaptation (1)
- Planar motor (1)
- Planar switched reluctance motor (PSRM) (1)
- Position estimation (1)
- Precision positioning (1)
- Sensorless control (1)
- Sliding mode observer (SMO) (1)
- Speaker diarization (1)
- Speaker embedding (1)
- Speaker verification (1)
- Switched reluctance motor (1)
- Trap-state density (1)
- Variational Bayes (1)
Articles 1 - 6 of 6
Full-Text Articles in Engineering
Introducing Phonetic Information To Speaker Embedding For Speaker Verification, Yi Liu, Liang He, Michael T. Johnson
Introducing Phonetic Information To Speaker Embedding For Speaker Verification, Yi Liu, Liang He, Michael T. Johnson
Electrical and Computer Engineering Faculty Publications
Phonetic information is one of the most essential components of a speech signal, playing an important role for many speech processing tasks. However, it is difficult to integrate phonetic information into speaker verification systems since it occurs primarily at the frame level while speaker characteristics typically reside at the segment level. In deep neural network-based speaker verification, existing methods only apply phonetic information to the frame-wise trained speaker embeddings. To improve this weakness, this paper proposes phonetic adaptation and hybrid multi-task learning and further combines these into c-vector and simplified c-vector architectures. Experiments on National Institute of Standards and Technology …
Enhanced Crystallinity Of Triple-Cation Perovskite Film Via Doping Nh4Scn, Ziji Liu, Detao Liu, Hao Chen, Long Ji, Hualin Zheng, Yiding Gu, Feng Wang, Zhi Chen, Shibin Li
Enhanced Crystallinity Of Triple-Cation Perovskite Film Via Doping Nh4Scn, Ziji Liu, Detao Liu, Hao Chen, Long Ji, Hualin Zheng, Yiding Gu, Feng Wang, Zhi Chen, Shibin Li
Electrical and Computer Engineering Faculty Publications
The trap-state density in perovskite films largely determines the photovoltaic performance of perovskite solar cells (PSCs). Increasing the crystal grain size in perovskite films is an effective method to reduce the trap-state density. Here, we have added NH4SCN into perovskite precursor solution to obtain perovskite films with an increased crystal grain size. The perovskite with increased crystal grain size shows a much lower trap-state density compared with reference perovskite films, resulting in an improved photovoltaic performance in PSCs. The champion photovoltaic device has achieved a power conversion efficiency of 19.36%. The proposed method may also impact other optoelectronic …
Latent Class Model With Application To Speaker Diarization, Liang He, Xianhong Chen, Can Xu, Yi Liu, Jia Liu, Michael T. Johnson
Latent Class Model With Application To Speaker Diarization, Liang He, Xianhong Chen, Can Xu, Yi Liu, Jia Liu, Michael T. Johnson
Electrical and Computer Engineering Faculty Publications
In this paper, we apply a latent class model (LCM) to the task of speaker diarization. LCM is similar to Patrick Kenny’s variational Bayes (VB) method in that it uses soft information and avoids premature hard decisions in its iterations. In contrast to the VB method, which is based on a generative model, LCM provides a framework allowing both generative and discriminative models. The discriminative property is realized through the use of i-vector (Ivec), probabilistic linear discriminative analysis (PLDA), and a support vector machine (SVM) in this work. Systems denoted as LCM-Ivec-PLDA, LCM-Ivec-SVM, and LCM-Ivec-Hybrid are introduced. In addition, three …
Automatic Look-Up Table Based Real-Time Phase Unwrapping For Phase Measuring Profilometry And Optimal Reference Frequency Selection, Jianwen Song, Daniel L. Lau, Yo-Sung Ho, Kai Liu
Automatic Look-Up Table Based Real-Time Phase Unwrapping For Phase Measuring Profilometry And Optimal Reference Frequency Selection, Jianwen Song, Daniel L. Lau, Yo-Sung Ho, Kai Liu
Electrical and Computer Engineering Faculty Publications
For temporal phase unwrapping in phase measuring profilometry, it has recently been reported that two phases with co-prime frequencies can be absolutely unwrapped using a look-up table; however, frequency selection and table construction has been performed manually without optimization. In this paper, a universal phase unwrapping method is proposed to unwrap phase flexibly and automatically by using geometric analysis, and thus we can programmatically build a one-dimensional or two-dimensional look-up table for arbitrary two co-prime frequencies to correctly unwrap phases in real time. Moreover, a phase error model related to the defocus effect is derived to figure out an optimal …
Sliding-Mode-Observer-Based Position Estimation For Sensorless Control Of The Planar Switched Reluctance Motor, Jundi Sun, Guang-Zhong Cao, Su-Dan Huang, Yeping Peng, Jiangbiao He, Qing-Quan Qian
Sliding-Mode-Observer-Based Position Estimation For Sensorless Control Of The Planar Switched Reluctance Motor, Jundi Sun, Guang-Zhong Cao, Su-Dan Huang, Yeping Peng, Jiangbiao He, Qing-Quan Qian
Electrical and Computer Engineering Faculty Publications
This paper proposes a position estimation method for a planar switched reluctance motor (PSRM). In the method, a second-order sliding mode observer (SMO) is used to achieve sensorless control of a PSRM for the first time. A sensorless closed-loop control strategy based on the SMO without a position sensor for the PSRM is constructed. The SMO mainly consists of a flux linkage estimation, an adaptive current estimation, an observing error calculation, and a position estimation section. An adaptive current observer is applied in the current estimation section to minimize the error between the measured and estimated currents and to increase …
Design And Analysis Of Long-Stroke Planar Switched Reluctance Motor For Positioning Applications, Su-Dan Huang, Guang-Zhong Cao, Yeping Peng, Chao Wu, Deliang Liang, Jiangbiao He
Design And Analysis Of Long-Stroke Planar Switched Reluctance Motor For Positioning Applications, Su-Dan Huang, Guang-Zhong Cao, Yeping Peng, Chao Wu, Deliang Liang, Jiangbiao He
Electrical and Computer Engineering Faculty Publications
This paper presents the design, control, and experimental performance evaluation of a long-stroke planar switched reluctance motor (PSRM) for positioning applications. Based on comprehensive consideration of the electromagnetic and mechanical characteristics of the PSRM, a motor design is first developed to reduce the force ripple and deformation. A control scheme with LuGre friction compensation is then proposed to improve the positioning accuracy of the PSRM. Furthermore, this control scheme is proven to ensure the stable motion of the PSRM system. Additionally, the response speed and steady-state error of the PSRM system with this control scheme are theoretically analyzed. Finally, the …