2022 IEEE Ninth International Conference on Communications and Electronics (ICCE)最新文献_第4页

Speaker Diarization For Vietnamese Conversations Using Deep Neural Network Embeddings 基于深度神经网络嵌入的越南语会话的说话人分类

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852042

Tung Lam Nguyen, Bao Thang Ta, Van Hai Do, T. Tran, Nhat Minh Le

{"title":"Speaker Diarization For Vietnamese Conversations Using Deep Neural Network Embeddings","authors":"Tung Lam Nguyen, Bao Thang Ta, Van Hai Do, T. Tran, Nhat Minh Le","doi":"10.1109/ICCE55644.2022.9852042","DOIUrl":"https://doi.org/10.1109/ICCE55644.2022.9852042","url":null,"abstract":"Speaker diarization, known as finding “who spoke when” is the method of dividing a conversation into segments spoken by the same speaker. While speaker diarization has numerous applications, there are little to no reports on its application in Vietnamese speech processing system. In addition, the key to accurately do such task is to learn discriminative speaker representations, or speaker embeddings. Recently X-Vectors and ECAPA-TDNN, based on deep neural networks, has emerged as state-of-the-art speaker embeddings networks for English corpora. In this work, we build a speaker diarization system for Vietnamese telephone conversations, and explore the capabilities of X-Vectors and ECAPA-TDNN in the system. We also evaluate the discriminative characteristics of these speaker embeddings networks on a bare-bones speaker verification system. Used data include proprietary datasets (IPCC-110000, IPCC-2000, VTR-1350) and a public dataset (ZALO-400). While these datasets can be used directly for training and testing for speaker verification task, for speaker diarization task we have to simulate multi-way conversations. Our conducted experiments show that ECAPA-TDNN system out-perform the X-Vectors system on both speaker verification and speaker diarization tasks.","PeriodicalId":388547,"journal":{"name":"2022 IEEE Ninth International Conference on Communications and Electronics (ICCE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131791805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Dual-Band Widebeam Dual-Polarized Antenna for Full-Duplex Communications 全双工通信用双频宽波束双极化天线

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852105

S. Ta, N. Nguyen-Trong

{"title":"Dual-Band Widebeam Dual-Polarized Antenna for Full-Duplex Communications","authors":"S. Ta, N. Nguyen-Trong","doi":"10.1109/ICCE55644.2022.9852105","DOIUrl":"https://doi.org/10.1109/ICCE55644.2022.9852105","url":null,"abstract":"This paper proposes an in-band full-duplex (IBFD) antenna with dual-band widebeam dual-polarized radiation. The antenna is composed of two orthogonal dual-band printed dipoles, i.e., one is with a single-ended feed for the transmitting (Tx) and the other is with a differential feed for the receiving (Rx). A high isolation among Tx and Rx ports is achieved by exploiting the symmetry of the design, which is maintained by modifying the feeding and structure of the printed dipoles. Two techniques of angled-dipole and cavity-backed reflector are employed to broaden the beamwidth in the lower and upper bands, respectively. A dual-band design operating at 2.45/5.8 GHz is characterized. A wideband out-of-phase power divider is employed to realize the differential-feed. The antenna achieves a 10-dB return loss bandwidth of 2.35 – 2.53 GHz and 5.64 – 6.02 GHz and Tx-to-Rx port isolation of ≥43 dB. Moreover, the full-wave simulator results in a cross-polarization level of ≤–30 dB, a realized gain of 6.0 dBi and 4.5 dBi, and a 3-dB beamwidth of broader than 88° and 120° at the lower and upper bands, respectively.","PeriodicalId":388547,"journal":{"name":"2022 IEEE Ninth International Conference on Communications and Electronics (ICCE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131792292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

DC-link Capacitor Voltage Balancing Control without Auxiliary Circuits for Five-level Hybrid T-type Neural-Point Clamped Inverters 五电平混合t型神经点箝位逆变器无辅助电路直流电容电压平衡控制

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852090

Min-Seok Kim, Dong-Choon Lee

引用次数: 2

Empirical Study of RepPoints Representation for Object Detection in Aerial Images 航空图像中目标检测RepPoints表示的实证研究

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852099

Thinh V. Le, Huyen Ngoc N. Van, Doanh C. Bui, Phuong Vo, Nguyen D. Vo, Khang Nguyen

{"title":"Empirical Study of RepPoints Representation for Object Detection in Aerial Images","authors":"Thinh V. Le, Huyen Ngoc N. Van, Doanh C. Bui, Phuong Vo, Nguyen D. Vo, Khang Nguyen","doi":"10.1109/ICCE55644.2022.9852099","DOIUrl":"https://doi.org/10.1109/ICCE55644.2022.9852099","url":null,"abstract":"Anchor-based detectors have dominated object detection for several years. These rely heavily on rectangular bounding boxes representation, which is convenient to use but reveals severe limitations, causing the inaccurate location of the objects with dense distribution or arbitrary direction. In this paper, we first utilize a new finer representation of objects, RepPoints (representative points), for improved feature extraction and object localization on aerial traffic images. Then, we experimentally fine-tuned the RPDet – an anchor-free object detector based on RepPoints – to prove that this approach can achieve the same effective performance as the state-of-the-art anchor-based detection methods. Our experimental modifications include the adoption of advanced models such as ResNet50, ResNeXt101 and Res2Net101 as backbone; Besides, we implement modules of DCN (Deformable Convolution Networks) for backbone architecture. To the best of our knowledge, the modified system is the current best performer on the task of object detection with 23.6% in AP and 42.8% in AP50 on the VISDRONE-DET detection benchmark.","PeriodicalId":388547,"journal":{"name":"2022 IEEE Ninth International Conference on Communications and Electronics (ICCE)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133816742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

A novel method for quantification of vacant parking spaces at on-street parking lots 一种新的街道停车场空置车位量化方法

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852046

Kieu-Ha Phung, Q. Huy, Nguyen Le, Dat Tran, Duc-Tuan Pham, Xuan Vu Phan, Thang Nguyen

{"title":"A novel method for quantification of vacant parking spaces at on-street parking lots","authors":"Kieu-Ha Phung, Q. Huy, Nguyen Le, Dat Tran, Duc-Tuan Pham, Xuan Vu Phan, Thang Nguyen","doi":"10.1109/ICCE55644.2022.9852046","DOIUrl":"https://doi.org/10.1109/ICCE55644.2022.9852046","url":null,"abstract":"Intelligence transportations in crowed urban cities will surely need the thoroughly management of parking spaces, especially when the number of vehicles increases quickly, and autonomous driving vehicles will be more popular. Monitoring and real-time updating available vacant slots will be essential. In this work, we propose a camera-based monitoring solution for on-street parking spaces which are in open area, freely entering/leaving and connected with surround landscape. Our solution does not require to install physical markers at fields, however, can assess the space of a parking vehicle required on field, and report the number of available vacant slots on the field. The accuracy of the proposed algorithm has been evaluated by the data collected from an on-street parking areas nearby the university campus. It achieves the accuracy of approximate 96%, which is slightly 2% less than the results of the marker-based method. The program is lightweight that can be deployed on edge devices attached to CCTV cameras, hence, saving the bandwidth of sending data to central systems.","PeriodicalId":388547,"journal":{"name":"2022 IEEE Ninth International Conference on Communications and Electronics (ICCE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127894412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning Models for Skeleton-Based Action Recognition for UAVs 无人机基于骨架动作识别的深度学习模型

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852103

Dinh-Tan Pham, Van-Nam Hoang, Viet-Duc Le, Tien Nguyen, Thanh-Hai Tran, Hai Vu, Van-Hung Le, Thi-Lan Le

引用次数: 1

Performance Evaluation of the Angle of Arrival of LoRa Signals under Interference 干扰下LoRa信号到达角性能评价

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852102

Zeaiter Hussein, Spies Francois, Baala Oumaya, V. Thierry

{"title":"Performance Evaluation of the Angle of Arrival of LoRa Signals under Interference","authors":"Zeaiter Hussein, Spies Francois, Baala Oumaya, V. Thierry","doi":"10.1109/ICCE55644.2022.9852102","DOIUrl":"https://doi.org/10.1109/ICCE55644.2022.9852102","url":null,"abstract":"Tracking objects in indoor is always a challenge for a variety of Internet of Things (IoT) applications. Nowadays, many indoor tracking applications use Low-Power Wide-Area Networks (LPWAN) for Machine-to-Machine (M2M) communication. LoRa is a promising LPWAN radio communication technology designed for wide-area coverage and low-power embedded IoT devices. The objective of this paper is to evaluate the performance of the Angle of Arrival (AoA) direction finding approach in an indoor environment. The AoA performance of the LoRa signal is evaluated using different modulation settings, including Channel Bandwidth (BW) and spreading factor (SF). We measure the AoA accuracy of the LoRa signal using an individual Universal Software Radio Peripheral (USRP) B210, Software Defined Radio (SDR) receiver with the help of the GNU radio software development toolkit. In addition, a new approach to measure the AoA of LoRa signal under interference is investigated. We show that by using the Autocorrelation function combined with our direction finding algorithm, the detection and measurement of two simultaneous receptions is possible. The entire experimental setup was implemented in our indoor office environment.","PeriodicalId":388547,"journal":{"name":"2022 IEEE Ninth International Conference on Communications and Electronics (ICCE)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132413046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Fast-Lock Technique for Digital Sub-Sampling Fractional-N Phase-Locked-Loops 数字次采样分数n锁相环的快速锁相技术

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852054

Tuan Minh Vo, Tri Ngo-Minh

引用次数: 1

A Compact 50W GaN MMIC Power Amplifier for C-band applications c波段应用的50W GaN MMIC功率放大器

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852079

N. Nguyen, Sanghun Lee, C. Huynh

引用次数: 0

Reduction of Harmonics and Inverter Temperature in Experimental GaN-based Motor Drive System at High Frequencies Using LC Filter 利用LC滤波器降低实验gan电机驱动系统高频谐波和逆变器温度

2022 IEEE Ninth International Conference on Communications and Electronics (ICCE) Pub Date : 2022-07-27 DOI: 10.1109/ICCE55644.2022.9852038

N. M. Thao, Kenya Naruse, K. Fujisaki

引用次数: 0