检索结果-内蒙古大学图书馆

Dual-Path Spectrogram Refinement Network for Robust Speaker Verification

Journal of Shanghai Jiaotong University (science) 2025年 1-9页

作者： Wang, Zonghui Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The accuracy and reliability of automatic speaker verification (ASV) face significant challenges in noisy environments. In recent years, joint training of speech enhancement front-end and ASV back-end has been widely applied to improve the robustness of ASV systems. Traditional joint training directly uses the enhanced speech features as the input of the back-end. However, the diversity of noise types and noise intensities will excessively suppress the enhanced features, resulting in speech distortion or residual noise. To alleviate this problem, we propose a dual-path spectrogram refinement network that enables the enhanced features to learn supplementary information from the separated noise features. In addition, we incorporate coordinate attention into the overall joint architecture to capture more comprehensive frequency and temporal information of the speaker from different spatial positions. We conduct extensive experiments on the VoxCeleb1 test set, the out-of-domain noise test set, and the VOiCES corpus. The experimental results demonstrate that our proposed method significantly improves the accuracy and robustness of speaker verification systems in both clean and noisy environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Position Determination from CSI Measurements of Multiple UEs under Unaware Environment 16

Position Determination from CSI Measurements of Multiple UEs...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Wang, Chenchen Ma, Yubin Yu, Fangrui Wen, Hao Liu, Weiyu Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

In urban environment, communication signals encompass non-line-of-sight (NLOS) paths that contain environmental information. This paper investigates utilizing NLOS component signal to estimate the environment parameters, and uses these environmental parameters to achieve blind UEs (User Equipment) positioning. Specifically, this paper first analyzes the relationship between environmental parameters and the time of arrival (TOA) of NLOS signals. Second, an algorithm is proposed that utilizes the TOA of one-order NLOS signals in uplink signals between distributed UEs and base stations (BS) to estimate environmental parameters via maximum likelihood estimation. Subsequently, leveraging the obtained environmental parameters, achieving the positioning of blind UEs. Finally, numerical simulations validate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Reflection Non line of sight propagation Mirrors Reconstruction algorithms Environmental sensing Mirror surfaces Point clouds LIDAR Monte Carlo methods Numerical simulations

来源：评论

学校读者我要写书评

暂无评论

Compressed Sampling Time Difference of Arrival Estimation Method based on Amplitude and Phase Clustering 16

Compressed Sampling Time Difference of Arrival Estimation Me...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Jiao, Yang Wang, Chenchen Zhai, Jingyu Liu, Yipeng Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

In the realm of signal processing, modulation signals like PSK (Phase Shift Keying) and QAM (Quadrature Amplitude Modulation) can achieve a substantial signal-to-noise ratio enhancement through aliasing transmission subsequent to clustering and sorting. This paper introduces a novel approach to compressed Time Difference of Arrival (TDOA) estimation, leveraging amplitude-phase clustering signals. The compression matrix is meticulously crafted based on the distinctive amplitude and phase characteristics. Subsequently, the study delves into an analysis of the Cramer-Rao Lower Bound (CRLB) under full sampling conditions. Ultimately, TDOA estimation is carried out employing the Approximate Maximum Likelihood (AML) method. Simulation outcomes underscore the commendable performance of compressed sampling TDOA estimation predicated on amplitude and phase clustering, falling within an order of magnitude of that achieved through full sampling. © 2025 SPIE.

关键词： Quadrature amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

A Novel Environment Reconstruction Method based on Distributed NLOS signals 16

A Novel Environment Reconstruction Method based on Distribut...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Yu, Fangrui Li, Junlin Xie, Wei Zhang, Kehao Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Integrated Sensing and Communication (ISAC) is a rapidly evolving field with extensive application prospects. Environmental reconstruction (ER) is an important content of ISAC. Existing ER techniques often require large sample sizes or specific signals, which significantly limit their application. User Equipments (UEs) widely distributed in the environment and their communication signals provide an adequate measurement basis. However, there are challenges in utilizing communication signals due to limited research, and difficulties in identifying and extracting Non-Line-of-Sight (NLOS) signals. This paper proposes a distributed ER algorithm based on Angle of Arrival (AOA) and Time of Flight (TOF) information of NLOS signals, enabling identification and utilization of various order NLOS signals under complex NLOS conditions. A series of simulation delays validate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Non line of sight propagation Reflection Reconstruction algorithms Mirror pointing signal processing Environmental sensing Wireless communications

来源：评论

学校读者我要写书评

暂无评论

Pseudo-linear Approach to Joint LOS and NLOS Localization 16

Pseudo-linear Approach to Joint LOS and NLOS Localization

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Lv, Meng Rou Li, Bei Ning Chang, Xuan Yu Qin, Hao Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Wireless indoor positioning currently has a wider range of application, and high-precision positioning is considered a key capability after 5G. Angle-of-Arrival (AOA) and Time-of-arrival (TOA) positioning techniques has received widespread attention because it requires only two base stations and does not need synchronization time to complete the positioning. However, the disadvantage is that a small angle measurement error will have a large impact on the positioning accuracy. In this paper, an approach to joint line-of-sight (LOS) and non-line-of-sight (NLOS) localization based on TOA and AOA measurements of both direct and reflected paths was proposed. In addition, a pseudo-linear algorithm was used to provide a closed form solution for localization. The effect of measurement errors on pseudo-linear estimation was analyzed to enhance estimation accuracy and compare it with maximum likelihood estimation and CRLB (Cramér-Rao Lower Bound). Simulation results indicate that the positioning model and error analysis employed in this study are feasible and meet the requirements for high-precision positioning. © 2025 SPIE.

关键词： Time of arrival

来源：评论

学校读者我要写书评

暂无评论

Comparison of CRB on TOA Estimation of LOS Path between Incoherent and Coherent processing of Two Subbands CSI Measurements 16

Comparison of CRB on TOA Estimation of LOS Path between Inco...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Fan, Yiting Liu, Yi Sun, Luyao Liu, Yipeng Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Compared with the Wi-Fi received signal strength (RSS) commonly used in indoor localization, channel state information (CSI) contains physical layer information such as amplitude and phase of each subcarrier during signal transmission. Therefore, the indoor localization based on (CSI) can achieve higher accuracy, which has been widely used. However, when bandwidth is insufficient, it is challenging to distinguish the multiple-path components in CSI. In order to further improve the estimated accuracy of the line of sight (LOS) path time of arrival (TOA), multiple subbands are considered. In this paper, the Cramer-Rao Bounds (CRBs) of multiple-path TOA estimation for coherent and non-coherent processing of two subbands are derived. In addition, a concise approximate of CRB on TOA of LOS path is given, which can directly reveal the effect of key variables, such as time delay and phase difference between two subbands. Through simulation, the performance of single subband, coherent and non-coherent processing of two subbands are compared, and the hyper-coherent effect on LOS path TOA estimation with two subbands is verified. © 2025 SPIE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Performance Bound on Blind Estimation of Environmental Parameters and Radiation Source Locations with Misspecified Multipath TOA Measurements 16

Performance Bound on Blind Estimation of Environmental Param...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Wen, Hao Jiao, Yang Zhang, Kehao Peng, Xiangyu Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

Multipath propagation has attracted extensive attention due to its inclusion of environmental information. However, it is difficult to match multipath with the environment without a priori knowledge, making it challenging to exploit multipath. This paper focuses on the performance bound of the estimation problem in a rectangular room. Due to the lack of parameter information of the room in base station (BS), the estimation of environmental parameters and locations of user equipment (UE) distributed in the room are blind estimation problems. Measurements are the time of arrival (TOA) of first-order non-line-of-sight (NLOS) paths and line-of-sight (LOS) path between the BS and UEs, but the specific pairing between NLOS paths and the environment remains unknown. The paper first describes the pairing problem, which causes misspecified multipath TOA measurements, and subsequently derives the likelihood function and the performance bound known as the misspecified Cramer-Rao bound (MCRB) under various pairing conditions. Simulation results demonstrate that only under correct pairings or just a few wrong pairings, the MCRB will significantly less than the other case. © 2025 SPIE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

TDOA Estimation Method Based on Frequency Domain Decimation 16

TDOA Estimation Method Based on Frequency Domain Decimation

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Zhai, Jingyu Wang, Chenchen Jiao, Yang Liu, Yipeng Wan, Qun Nation Key Laboratory on Blind Signal Processing School of Information and Communication Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

The estimation of Time Difference of Arrival (TDOA) stands as a pivotal aspect of TDOA localization. This paper explores the TDOA estimation method utilizing decimation compression sampling for general signals and introduces a decimation compression sampling technique grounded in convex optimization. Simulation outcomes reveal that for signals possessing limited frequency domain sparsity, the data compression methodology advocated in this paper, in contrast to the traditional decimation compression method predicated on amplitude spectrum sorting, notably mitigates the root mean square error (RMSE) performance loss in Time Difference Maximum Likelihood Estimation (MLE). © 2025 SPIE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

The Analysis of Indoor High-precision Positioning Performance using Dual-panel System 16

The Analysis of Indoor High-precision Positioning Performanc...

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Ma, Yubin Lv, Mengrou Sun, Luyao Li, Junlin Wan, Qun School of Information and Communication Engineering Nation Key Laboratory on Blind Signal Processing University of Electronic Science and Technology of China Sichuan Chengdu611731 China

ISBN: (纸本)9781510689251

This paper investigates the high-precision positioning capabilities of a dual-panel system operating in the millimeter-wave frequency band. It begins by highlighting the significance of high-precision positioning technologies. Additionally, it provides background on the advantages and challenges associated with millimeter-wave frequencies. The study introduces a novel method to enhance positioning accuracy. This method extends the baseline using reflecting surfaces and eliminates time discrepancies between Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) signals. The effectiveness of the proposed method is evaluated through a Cramér-Rao Lower Bound (CRLB) analysis. This analysis compares single-panel and dual-panel systems under various conditions, including considerations of transceiver delay. Simulation experiments demonstrate that the dual-panel system significantly improves positioning accuracy compared to the single-panel system. This improvement is consistent regardless of transceiver delay. The results indicate that the dual-panel system effectively mitigates multipath effects and NLOS conditions. As a result, there is enhanced positioning stability and accuracy. These findings provide valuable insights and methodologies for advancing indoor positioning technologies. © 2025 SPIE.

关键词： Transceivers

来源：评论

学校读者我要写书评

暂无评论

Misspecified CRB for TDOA based Passive Localization 16

Misspecified CRB for TDOA based Passive Localization

引用

16th International Conference on signal processing Systems, ICSPS 2024

作者： Cao, Jingmin Wan, Qun Chen, Ying Du, Fen Liu, Yang Li, Wei University of Electronic Science and Technology of China Chengdu China Southwest China Institute of Electronic Technology Chengdu China National Key Laboratory on Blind Signal Processing Chengdu China

ISBN: (纸本)9781510689251

Misspecified CRB (MCRB) is a lower bound on the variance of estimators when the parametric mode is not fully characterizing the behavior of the measurements. This paper derives the TDOA localization model and the performance bound under misspecification of the mean value of the measurement noise. The MCRB can not only play the same role as the CRB but also be used to assess performance under misspecified model. It’s a generalization of the classical CRB to misspecified model framework. For comparison, the specified CRB for TDOA localization with non-zero-mean Gaussian model is aslo investigaed. MCRB is equate to the specified CRB when the mean value of the measurement noise is equal to zero. The simmulation results are satisfy the theoretical analysis. © 2025 SPIE.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：