咨询与建议

限定检索结果

文献类型

  • 4 篇 会议
  • 2 篇 期刊文献

馆藏范围

  • 6 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 6 篇 工学
    • 5 篇 计算机科学与技术...
    • 3 篇 软件工程
    • 2 篇 电气工程
    • 1 篇 电子科学与技术(可...
    • 1 篇 信息与通信工程
    • 1 篇 控制科学与工程
    • 1 篇 测绘科学与技术
  • 2 篇 理学
    • 2 篇 物理学
  • 2 篇 医学
    • 2 篇 临床医学
  • 1 篇 历史学
    • 1 篇 考古学
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 6 篇 dynamical variat...
  • 1 篇 structured seque...
  • 1 篇 variational infe...
  • 1 篇 kalmannet
  • 1 篇 dynamic bayesian...
  • 1 篇 dense target enc...
  • 1 篇 noise measuremen...
  • 1 篇 unsupervised spe...
  • 1 篇 hierarchical tax...
  • 1 篇 deep dynamical g...
  • 1 篇 kalman filter
  • 1 篇 speech enhanceme...
  • 1 篇 speech spectrogr...
  • 1 篇 nonnegative matr...
  • 1 篇 open-world learn...
  • 1 篇 deep state space...
  • 1 篇 inference algori...
  • 1 篇 speech analysis-...
  • 1 篇 time-domain anal...
  • 1 篇 recording

机构

  • 1 篇 univ grenoble al...
  • 1 篇 shenzhen univ bi...
  • 1 篇 cent supelec iet...
  • 1 篇 ietr cent supele...
  • 1 篇 department of co...
  • 1 篇 tianjin univ col...
  • 1 篇 ietr cent supele...
  • 1 篇 department of da...
  • 1 篇 department of el...
  • 1 篇 univ grenoble al...
  • 1 篇 guangzhou univ c...
  • 1 篇 univ grenoble al...
  • 1 篇 department of ar...
  • 1 篇 univ grenoble al...
  • 1 篇 nanjing univ inf...
  • 1 篇 sun yat sen univ...
  • 1 篇 sun yat sen univ...
  • 1 篇 univ grenoble al...
  • 1 篇 univ grenoble al...

作者

  • 3 篇 alameda-pineda x...
  • 3 篇 girin laurent
  • 3 篇 leglaive simon
  • 2 篇 bie xiaoyu
  • 1 篇 feng pengxing
  • 1 篇 dong yining
  • 1 篇 liu ziqi
  • 1 篇 liu gelu
  • 1 篇 shen dan
  • 1 篇 ma yuexin
  • 1 篇 hu jiaocheng
  • 1 篇 lin xiaoyu
  • 1 篇 yu zhizhi
  • 1 篇 tang shiqin
  • 1 篇 hueber thomas
  • 1 篇 zhang peng
  • 1 篇 chen junyang
  • 1 篇 li qincai
  • 1 篇 zhu xiangwei
  • 1 篇 chen xiaojun

语言

  • 6 篇 英文
检索条件"主题词=Dynamical Variational Autoencoders"
6 条 记 录,以下是1-10 订阅
排序:
dynamical variational autoencoders and KalmanNet: New Approaches to Robust High-Precision Navigation  5
Dynamical Variational Autoencoders and KalmanNet: New Approa...
收藏 引用
5th International-Society-for-Photogrammetry-and-Remote-Sensing (ISPRS) Geospatial Week (GSW)
作者: Shen, Dan Ma, Yuexin Liu, Gelu Hu, Jiaocheng Weng, Qizhen Zhu, Xiangwei Sun Yat Sen Univ Sch Syst Sci & Engn Guangzhou 510006 Peoples R China Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen 528406 Peoples R China
Kalman filters, recognized as a traditional and effective inference algorithm based on state space models (SSM), have been extensively applied in the fields of navigation and mapping. However, their performance will d... 详细信息
来源: 评论
Unsupervised Speech Enhancement Using dynamical variational autoencoders
收藏 引用
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2022年 30卷 2993-3007页
作者: Bie, Xiaoyu Leglaive, Simon Alameda-Pineda, Xavier Girin, Laurent Univ Grenoble Alpes Inria Grenoble Rhone Alpes F-38000 Grenoble France Cent Supelec IETR UMR CNRS 6164 F-35576 Cesson Sevigne France Univ Grenoble Alpes GIPSA Lab CNRS Grenoble INP F-38402 Grenoble France
dynamical variational autoencoders (DVAEs) are a class of deep generative models with latent variables, dedicated to model time series of high-dimensional data. DVAEs can be considered as extensions of the variational... 详细信息
来源: 评论
A Benchmark of dynamical variational autoencoders applied to Speech Spectrogram Modeling  22
A Benchmark of Dynamical Variational Autoencoders applied to...
收藏 引用
Interspeech Conference
作者: Bie, Xiaoyu Girin, Laurent Leglaive, Simon Hueber, Thomas Alameda-Pineda, Xavier Univ Grenoble Alpes CNRS LJK INRIA F-38000 Grenoble France Univ Grenoble Alpes CNRS Grenoble INP GIPSA Lab F-38000 Grenoble France IETR Cent Supelec F-35576 Cesson Sevigne France
The variational Autoencoder (VAE) is a powerful deep generative model that is now extensively used to represent high-dimensional complex data via a low-dimensional latent space learned in an unsupervised manner. In th... 详细信息
来源: 评论
Unsupervised speech enhancement with deep dynamical generative speech and noise models  24
Unsupervised speech enhancement with deep dynamical generati...
收藏 引用
Interspeech Conference
作者: Lin, Xiaoyu Leglaive, Simon Girin, Laurent Alameda-Pineda, Xavier Univ Grenoble Alpes Inria Grenoble Rhone Alpes Grenoble France IETR Cent Supelec UMR CNRS 6164 Gif Sur Yvette France Univ Grenoble Alpes CNRS Grenoble INP GIPSA Lab Grenoble France
This work builds on a previous work on unsupervised speech enhancement using a dynamical variational autoencoder (DVAE) as the clean speech model and non-negative matrix factorization (NMF) as the noise model. We prop... 详细信息
来源: 评论
A Hierarchical Taxonomy For Deep State Space Models
A Hierarchical Taxonomy For Deep State Space Models
收藏 引用
2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025
作者: Tang, Shiqin Feng, Pengxing Yu, Shujian Dong, Yining Qin, S. Joe Department of Data Science City University of Hong Kong Hong Kong Department of Electrical Engineering City University of Hong Kong Hong Kong Department of Artificial Intelligence Vrije Universiteit Amsterdam Amsterdam Netherlands Department of Computing and Decision Science Lingnan University Hong Kong
Modeling nonlinear dynamical systems is a challenging task in fields such as speech processing, music generation, and video prediction. This paper introduces a hierarchical framework for Deep State Space Models (DSSMs... 详细信息
来源: 评论
Open-world structured sequence learning via dense target encoding
收藏 引用
INFORMATION SCIENCES 2024年 680卷
作者: Zhang, Qin Liu, Ziqi Li, Qincai Xiang, Haolong Yu, Zhizhi Chen, Junyang Zhang, Peng Chen, Xiaojun Shenzhen Univ Big Data Inst Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Nanjing Univ Informat Sci & Technol Sch Software Nanjing 210044 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Guangzhou Univ Cyberspace Inst Adv Technol Guangzhou 510006 Peoples R China
Structured sequences are popularly used to describe graph data with time-evolving node features and edges. A typical real-world scenario of structured sequences is that unknown class labels continuously arrive and thu... 详细信息
来源: 评论