This paper describes a novel approach to flexible control of speaker characteristics using tensor representation of multiple Gaussian mixture models (GMM). In voice conversion studies, realization of conversion from/to an arbitrary speaker's voice is one of the important objectives. For this purpose, eigenvoice conversion (EVC) based on an eigenvoice GMM (EV-GMM) was proposed. In the EVC, a speaker space is constructed based on GMM supervectors which are high-dimensional vectors derived by concatenating the mean vectors of each of the speaker GMMs. In the speaker space, each speaker is represented by a small number of weight parameters of eigen-supervectors. In this paper, we revisit construction of the speaker space by introducing the tensor factor analysis of training data set. In our approach, each speaker is represented as a matrix of which the row and the column respectively correspond to the dimension of the mean vector and the Gaussian component. The speaker space is derived by the tensor factor analysis of the set of the matrices. Our approach can solve an inherent problem of supervector representation, and it improves the performance of voice conversion. In addition, in this paper, effects of speaker adaptive training before factorization are also investigated. Experimental results of one-to-many voice conversion demonstrate the effectiveness of the proposed approach.

In this paper, an enhanced well-changed GGNMOS (EW-GGNMOS) is proposed and demonstrated. The new device has the same topology as the conventional 3.3V GGNMOS, except that its well has been changed to the 1.2V p-well. Attributed to higher doping concentration, resulting in a much lower trigger voltage and desirable turn-on uniformity compared to conventional 3.3V GGNMOS. Therefore, we can use EW-GGNMOS as a 3.3V ESD protection device without any additional process.

Outlier detection in a data set is very important in performing proper data mining. In this paper, we propose a method for efficiently detecting outliers by performing cluster analysis using the DS algorithm improved from the k-means algorithm. This method is simpler to detect outliers than traditional methods, and these detected outliers can quantitatively indicate “the degree of outlier”. Using this method, we detect abnormal trading days from OHLCs for S&P500 and FTSA, which are typical and world-wide stock indexes, from the beginning of 2005 to the end of 2015. They are defined as non-steady trading days, and the conditions for becoming the non-steady markets are mined as new knowledge. Applying the mined knowledge to OHLCs from the beginning of 2016 to the end of 2018, we can predict the non-steady trading days during that period. By verifying the predicted content, we show the fact that the appropriate knowledge has been successfully mined and show the effectiveness of the outlier detection method proposed in this paper. Furthermore, we mutually reference and comparatively analyze the results of applying this method to multiple stock indexes. This analyzes possible to visualize when and where social and economic impacts occur and how they propagate through the earth. This is one of the new applications using this method.

This letter studies the physical layer security of an unmanned aerial vehicle (UAV)-enabled multicasting system, where a UAV serves as a mobile transmitter to send a common confidential message to a group of legitimate users under the existence of multiple eavesdroppers. The worst situation in which each eavesdropper can wiretap all legitimate users is considered. We seek to maximize the average secrecy rate by jointly optimizing the UAV's transmit power and trajectory over a given flight period. The resulting optimization problem is nonconvex and intractable to solve. To circumvent the nonconvexity, we propose an iterative algorithm to approximate the solution based on the alternating optimization and successive convex approximation methods. Simulation results validate the convergence and effectiveness of our proposed algorithm.

This paper proposes a method for heatmapping people who are involved in a group activity. Such people grouping is useful for understanding group activities. In prior work, people grouping is performed based on simple inflexible rules and schemes (e.g., based on proximity among people and with models representing only a constant number of people). In addition, several previous grouping methods require the results of action recognition for individual people, which may include erroneous results. On the other hand, our proposed heatmapping method can group any number of people who dynamically change their deployment. Our method can work independently of individual action recognition. A deep network for our proposed method consists of two input streams (i.e., RGB and human bounding-box images). This network outputs a heatmap representing pixelwise confidence values of the people grouping. Extensive exploration of appropriate parameters was conducted in order to optimize the input bounding-box images. As a result, we demonstrate the effectiveness of the proposed method for heatmapping people involved in group activities.

This paper proposes a method to create various training images for instance segmentation in a semi-supervised manner. In our proposed learning scheme, a few 3D CG models of target objects and a large number of images retrieved by keywords from the Internet are employed for initial model training and model update, respectively. Instance segmentation requires pixel-level annotations as well as object class labels in all training images. A possible solution to reduce a huge annotation cost is to use synthesized images as training images. While image synthesis using a 3D CG simulator can generate the annotations automatically, it is difficult to prepare a variety of 3D object models for the simulator. One more possible solution is semi-supervised learning. Semi-supervised learning such as self-training uses a small set of supervised data and a huge number of unsupervised data. The supervised images are given by the 3D CG simulator in our method. From the unsupervised images, we have to select only correctly-detected annotations. For selecting the correctly-detected annotations, we propose to quantify the reliability of each detected annotation based on its silhouette as well as its textures. Experimental results demonstrate that the proposed method can generate more various images for improving instance segmentation.

Massive MIMO is known as a promising technology for multiuser multiplexing in the fifth generation mobile communication system to accommodate the rapidly-increasing traffic. It has a large number of antenna elements and thus provides very sharp beams. As seen in hybrid beamforming, there have already been many papers on the concatenation of two precoders (beamformers). The inner precoder, i.e., a multi-beam former, performs a linear transformation between the element space and the beam space. The outer precoder forms nulls in the limited beam space spanned by selected beams to suppress the inter-user interference. In this two-step precoder, the beam shape is expected to determine the system performance. In this paper, we evaluate the achievable throughput performance for different beam-shaping schemes: a discrete Fourier transform (DFT) beam, Chebyshev weighted beams, and Taylor weighted beam. Simulations show that the DFT beam provides the best performance except the case of imperfect precoding and cell edge SNR of 30dB.

Software fault localization, as one of the essential activities in program debugging, aids to software developers to identify the locations of faults in a program, thus reducing the cost of program debugging. Spectrum-based fault localization (SBFL), as one of the representative localization techniques, has been intensively studied. The localization technique calculates the probability of each program entity that is faulty by a certain suspiciousness formula. The accuracy of SBFL is not always as satisfactory as expected because it neglects the contextual information of statement executions. Therefore, we proposed 5 rules, i.e., random, the maximum coverage, the minimum coverage, the maximum distance, and the minimum distance, to improve the accuracy of SBFL for further. The 5 rules can effectively use the contextual information of statement executions. Moreover, they can be implemented on the traditional SBFL techniques using suspiciousness formulas with little effort. We empirically evaluated the impacts of the rules on 17 suspiciousness formulas. The results show that all 5 rules can significantly improve the ranking of faulty statements. Particularly, for the faults difficult to locate, the improvement is more remarkable. Generally, the rules can effectively reduce the number of statements examined by an average of more than 19%. Compared with other rules, the minimum coverage rule generates better results. This indicates that the application of the test case having the minimum coverage capability for fault localization is more effective.

Survivable virtual network embedding (SVNE) is one of major challenges of network virtualization. In order to improve the utilization rate of the substrate network (SN) resources with virtual network (VN) topology connectivity guarantee under link failure in SN, we first establishes an Integer Linear Programming (ILP) model for that under SN supports path splitting. Then we designs a novel survivable VN topology protection method based on particle swarm optimization (VNE-PSO), which redefines the parameters and related operations of particles with the embedding overhead as the fitness function. Simulation results show that the solution significantly improves the long-term average revenue of the SN, the acceptance rate of VN requests, and reduces the embedding time compared with the existing research results.

End-to-end (E2E) multilingual automatic speech recognition (ASR) systems aim to recognize multilingual speeches in a unified framework. In the current E2E multilingual ASR framework, the output prediction for a specific language lacks constraints on the output scope of modeling units. In this paper, a language supervision training strategy is proposed with language masks to constrain the neural network output distribution. To simulate the multilingual ASR scenario with unknown language identity information, a language identification (LID) classifier is applied to estimate the language masks. On four Babel corpora, the proposed E2E multilingual ASR system achieved an average absolute word error rate (WER) reduction of 2.6% compared with the multilingual baseline system.

Ferroelectric gate field-effect transistors (MFSFETs) were investigated utilizing nondoped HfO2 deposited by RF magnetron sputtering utilizing Hf target. After the post-metallization annealing (PMA) process with Pt top gate at 500°C/30s, ferroelectric characteristic of 10nm thick nondoped HfO2 was obtained. The fabricated MFSFETs showed the memory window of 1.7V when the voltage sweep range was from -3 to 3V.

In this paper, the effects of the TiN encapsulating layer and the dopant segregation process on the interface properties and the Schottky barrier height reduction of PdEr-silicide/n-Si(100) were investigated. The results show that controlling the initial location of the boron dopants by adding the TiN encapsulating layer lowered the Schottky barrier height (SBH) for hole to 0.20 eV. Furthermore, the density of interface states (Dit) on the order of 1011eV-1cm-2 was obtained indicating that the dopant segregation process with TiN encapsulating layer effectively annihilated the interface states.

We have investigated the in-situ N2-plasma nitridation for high-k HfN gate insulator formed by electron cyclotron resonance (ECR) plasma sputtering to improve the electrical characteristics. It was found that the increase of nitridation gas pressure for the deposited HfN1.1 gate insulator, such as 98 mPa, decreased both the hysteresis width in C-V characteristics and leakage current. Furthermore, the 2-step nitiridation process with the nitridation gas pressure of 26 mPa followed by the nitridation at 98 mPa realized the decrease of equivalent oxide thickness (EOT) to 0.9 nm with decreasing the hysteresis width and leakage current. The fabricated metal-insulator-semiconductor field-effect transistor (MISFET) with 2-step nitridation showed a steep subthreshold swing of 87 mV/dec.

This paper presents the feasibility of a capacitive coupler utilizing an electric double layer for wireless power transfer under seawater. Since seawater is an electrolyte solution, an electric double layer (EDL) is formed on the electrode surface of the coupler in direct current. If the EDL can be utilized in radio frequency, it is possible that high power transfer efficiency can be achieved under seawater because a high Q-factor can be obtained. To clarify this, the following steps need taking; First, measure the frequency characteristics of the complex permittivity in seawater and elucidate the behaviors of the EDL from the results. Second, clarify that EDL leads to an improvement in the Q-factor of seawater. It will be shown in this paper that capacitive coupling by EDL occurs using two kinds of the coupler models. Third, design a coupler with high efficiency as measured by the Q-factor and relative permittivity of EDL. Last, demonstrate that the designed coupler under seawater can achieve over 85% efficiency at a transfer distance of 5 mm and feasibility of the coupler with EDL.

High frame rate and ultra-low delay are the most essential requirements for building excellent human-machine-interaction systems. As a state-of-the-art local keypoint detection and feature extraction algorithm, A-KAZE shows high accuracy and robustness. Nonlinear scale space is one of the most important modules in A-KAZE, but it not only has at least one frame delay and but also is not hardware friendly. This paper proposes a hardware oriented nonlinear scale space for high frame rate and ultra-low delay A-KAZE matching system. In the proposed matching system, one part of nonlinear scale space is temporally forward and calculated in the previous frame (proposal #1), so that the processing delay is reduced to be less than 1 ms. To improve the matching accuracy affected by proposal #1, pre-adjustment of nonlinear scale (proposal #2) is proposed. Previous two frames are used to do motion estimation to predict the motion vector between previous frame and current frame. For further improvement of matching accuracy, pixel-level pre-adjustment (proposal #3) is proposed. The pre-adjustment changes from block-level to pixel-level, each pixel is assigned an unique motion vector. Experimental results prove that the proposed matching system shows average matching accuracy higher than 95% which is 5.88% higher than the existing high frame rate and ultra-low delay matching system. As for hardware performance, the proposed matching system processes VGA videos (640×480 pixels/frame) at the speed of 784 frame/second (fps) with a delay of 0.978 ms/frame.

High frame rate and ultra-low delay matching system plays an increasingly important role in human-machine interactions, because it guarantees high-quality experiences for users. Existing image matching algorithms always generate mismatches which heavily weaken the performance the human-machine-interactive systems. Although many mismatch removal algorithms have been proposed, few of them achieve real-time speed with high frame rate and low delay, because of complicated arithmetic operations and iterations. This paper proposes a temporal constraints and block weighting judgement based high frame rate and ultra-low delay mismatch removal system. The proposed method is based on two temporal constraints (proposal #1 and proposal #2) to firstly find some true matches, and uses these true matches to generate block weighting (proposal #3). Proposal #1 finds out some correct matches through checking a triangle route formed by three adjacent frames. Proposal #2 further reduces mismatch risk by adding one more time of matching with opposite matching direction. Finally, proposal #3 distinguishes the unverified matches to be correct or incorrect through weighting of each block. Software experiments show that the proposed mismatch removal system achieves state-of-the-art accuracy in mismatch removal. Hardware experiments indicate that the designed image processing core successfully achieves real-time processing of 784fps VGA (640×480 pixels/frame) video on field programmable gate array (FPGA), with a delay of 0.858 ms/frame.

Collaborative filtering (CF) is one of the most popular approaches to building Recommender systems (RS) and has been extensively implemented in many online applications. But it still suffers from the new user cold start problem that users have only a small number of items interaction or purchase records in the system, resulting in poor recommendation performance. Thus, we design a new similarity model which can fully utilize the limited rating information of cold users. We first construct a new metric, Popularity-Mean Squared Difference, considering the influence of popular items, average difference between two user's common ratings and non-numerical information of ratings. Moreover, the second new metric, Singularity-Difference, presents the deviation degree of favor to items between two users. It considers the distribution of the similarity degree of co-ratings between two users as weight to adjust the deviation degree. Finally, we take account of user's personal rating preferences through introducing the mean and variance of user ratings. Experiment results based on three real-life datasets of MovieLens, Epinions and Netflix demonstrate that the proposed model outperforms seven popular similarity methods in terms of MAE, precision, recall and F1-Measure under new user cold start condition.

This paper reviews our developed wide band human body communication technology for wearable and implantable robot control. The wearable and implantable robots are assumed to be controlled by myoelectric signals and operate according to the operator's will. The signal transmission for wearable robot control was shown to be mainly realized by electrostatic coupling, and the signal transmission for implantable robot control was shown to be mainly determined by the lossy frequency-dependent dielectric properties of human body. Based on these basic observations on signal transmission mechanisms, we developed a 10-50MHz band impulse radio transceiver based on human body communication technology, and applied it for wireless control of a robotic hand using myoelectric signals in the first time. In addition, we also examined its applicability to implantable robot control, and evaluated the communication performance of implant signal transmission using a living swine. These experimental results showed that the proposed technology is well suited for detection and transmission of biological signals for wearable and implantable robot control.

This study presents a method for improving the heartbeat interval accuracy of photoplethysmographic (PPG) sensors at ultra-low sampling rates. Although sampling rate reduction can extend battery life, it increases the sampling error and degrades the accuracy of the extracted heartbeat interval. To overcome these drawbacks, a sampling-error compensation method is proposed in this study. The sampling error is reduced by using linear interpolation and autocorrelation based on the waveform similarity of heartbeats in PPG. Furthermore, this study introduces two-line approximation and first derivative PPG (FDPPG) to improve the waveform similarity at ultra-low sampling rates. The proposed method was evaluated using measured PPG and reference electrocardiogram (ECG) of seven subjects. The results reveal that the mean absolute error (MAE) of 4.11ms was achieved for the heartbeat intervals at a sampling rate of 10Hz, compared with 1-kHz ECG sampling. The heartbeat interval error was also evaluated based on a heart rate variability (HRV) analysis. Furthermore, the mean absolute percentage error (MAPE) of the low-frequency/high-frequency (LF/HF) components obtained from the 10-Hz PPG is shown to decrease from 38.3% to 3.3%. This error is small enough for practical HRV analysis.

In machine translation (MT) mediated human-to-human communication, it is not an easy task to select the languages and translation services to be used as the users have various language backgrounds and skills. Our previous work introduced the best-balanced machine translation mechanism (BBMT) to automatically select the languages and translation services so as to equalize the language barriers of participants and to guarantee their equal opportunities in joining conversations. To assign proper languages to be used, however, the mechanism needs information of the participants' language skills, typically participants' language test scores. Since it is important to keep test score confidential, as well as other sensitive information, this paper introduces agents, which exchange encrypted information, and secure computation to ensure that agents can select the languages and translation services without destroying privacy. Our contribution is to introduce a multi-agent system with secure computation that can protect the privacy of users in multilingual communication. To our best knowledge, it is the first attempt to introduce multi-agent systems and secure computing to this area. The key idea is to model interactions among agents who deal with user's sensitive data, and to distribute calculation tasks to three different types of agents, together with data encryption, so no agent is able to access or recover participants' score.