Search Results for author: Pengcheng Zhu

Found 15 papers, 1 papers with code

MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization

no code implementations10 May 2024 Pengcheng Zhu, Yaoming Zhuang, Baoquan Chen, Li Li, Chengdong Wu, Zhanlin Liu

To address these limitations, we uniquely integrates advanced sparse visual odometry with a dense Gaussian Splatting scene representation for the first time, thereby eliminating the dependency on depth maps typical of Gaussian Splatting-based SLAM systems and enhancing tracking robustness.

Depth Estimation Novel View Synthesis +3

Trainable Joint Channel Estimation, Detection and Decoding for MIMO URLLC Systems

1 code implementation11 Apr 2024 Yi Sun, Hong Shen, Bingqing Li, Wei Xu, Pengcheng Zhu, Nan Hu, Chunming Zhao

The receiver design for multi-input multi-output (MIMO) ultra-reliable and low-latency communication (URLLC) systems can be a tough task due to the use of short channel codes and few pilot symbols.

Passive Integrated Sensing and Communication Scheme based on RF Fingerprint Information Extraction for Cell-Free RAN

no code implementations10 Nov 2023 Jingxuan Yu, Fan Zeng, Jiamin Li, Feiyang Liu, Pengcheng Zhu, Dongming Wang, Xiaohu You

This paper investigates how to achieve integrated sensing and communication (ISAC) based on a cell-free radio access network (CF-RAN) architecture with a minimum footprint of communication resources.

Multi-GradSpeech: Towards Diffusion-based Multi-Speaker Text-to-speech Using Consistent Diffusion Models

no code implementations21 Aug 2023 Heyang Xue, Shuai Guo, Pengcheng Zhu, Mengxiao Bi

Despite imperfect score-matching causing drift in training and sampling distributions of diffusion models, recent advances in diffusion-based acoustic models have revolutionized data-sufficient single-speaker Text-to-Speech (TTS) approaches, with Grad-TTS being a prime example.

Joint Uplink and Downlink Resource Allocation Towards Energy-efficient Transmission for URLLC

no code implementations25 May 2023 Kang Li, Pengcheng Zhu, Yan Wang, Fu-Chun Zheng, Xiaohu You

With the proposed packet delivery mechanism, we jointly optimize bandwidth allocation and power control of uplink and downlink, antenna configuration, and subchannel assignment to minimize the average total power under the constraint of URLLC transmission requirements.

DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding

no code implementations21 May 2023 Ziqian Ning, Yuepeng Jiang, Pengcheng Zhu, Jixun Yao, Shuai Wang, Lei Xie, Mengxiao Bi

Voice conversion is an increasingly popular technology, and the growing number of real-time applications requires models with streaming conversion capabilities.

Data Augmentation Decoder +2

Optimization of the energy efficiency in Smart Internet of Vehicles assisted by MEC

no code implementations14 Jan 2023 Jiafei Fu, Pengcheng Zhu, Jingyu Hua, Jiamin Li, Jiangang Wen

Smart Internet of Vehicles (IoV) as a promising application in Internet of Things (IoT) emerges with the development of the fifth generation mobile communication (5G).


Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features

no code implementations9 Nov 2022 Ziqian Ning, Qicong Xie, Pengcheng Zhu, Zhichao Wang, Liumeng Xue, Jixun Yao, Lei Xie, Mengxiao Bi

We further fuse the linguistic and para-linguistic features through an attention mechanism, where speaker-dependent prosody features are adopted as the attention query, which result from a prosody encoder with target speaker embedding and normalized pitch and energy of source speech as input.

Decoder Voice Conversion

Low Altitude 3-D Coverage Performance Analysis in Cell-Free Distributed Collaborative Massive MIMO Systems

no code implementations28 Jun 2022 Jiamin Li, Qijun Pan, Pengcheng Zhu, Dongming Wang, Xiaohu You

To improve the poor performance of distributed operation and non-scalability of centralized operation in traditional cell-free massive MIMO, we propose a cell-free distributed collaborative (CFDC) massive multiple-input multiple-output (MIMO) system based on a novel two-layer model to take advantages of the distributed cloud-edge-end collaborative architecture in beyond 5G (B5G) internet of things (IoT) environment to provide strong flexibility and scalability.

Content Popularity Prediction Based on Quantized Federated Bayesian Learning in Fog Radio Access Networks

no code implementations23 Jun 2022 Yunwei Tao, Yanxiang Jiang, Fu-Chun Zheng, Pengcheng Zhu, Dusit Niyato, Xiaohu You

To utilize the computing resources of other fog access points (F-APs) and to reduce the communications overhead, we propose a quantized federated learning (FL) framework combining with Bayesian learning.

Federated Learning

One-shot Voice Conversion For Style Transfer Based On Speaker Adaptation

no code implementations24 Nov 2021 Zhichao Wang, Qicong Xie, Tao Li, Hongqiang Du, Lei Xie, Pengcheng Zhu, Mengxiao Bi

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness.

Style Transfer Voice Conversion

VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis

no code implementations17 Oct 2021 Yongmao Zhang, Jian Cong, Heyang Xue, Lei Xie, Pengcheng Zhu, Mengxiao Bi

In this paper, we propose VISinger, a complete end-to-end high-quality singing voice synthesis (SVS) system that directly generates audio waveform from lyrics and musical score.

Decoder Singing Voice Synthesis +1

Privacy-preserving Channel Estimation in Cell-free Hybrid Massive MIMO Systems

no code implementations26 Jan 2021 Jun Xu, Xiaodong Wang, Pengcheng Zhu, Xiaohu You

We consider a cell-free hybrid massive multiple-input multiple-output (MIMO) system with $K$ users and $M$ access points (APs), each with $N_a$ antennas and $N_r< N_a$ radio frequency (RF) chains.

Low-Rank Matrix Completion Information Theory Signal Processing Information Theory

Multi-glance Reading Model for Text Understanding

no code implementations WS 2018 Pengcheng Zhu, Yujiu Yang, Wenqiang Gao, Yi Liu

Based on the multi-glance mechanism, we design two types of recurrent neural network models for repeated reading: Glance Cell Model (GCM) and Glance Gate Model (GGM).

Document Classification Machine Translation +2

Cannot find the paper you are looking for? You can Submit a new open access paper.