咨询与建议

限定检索结果

文献类型

  • 10 篇 期刊文献
  • 5 篇 会议

馆藏范围

  • 15 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 13 篇 工学
    • 7 篇 电气工程
    • 3 篇 信息与通信工程
    • 3 篇 计算机科学与技术...
    • 2 篇 生物医学工程(可授...
    • 1 篇 电子科学与技术(可...
    • 1 篇 航空宇航科学与技...
  • 4 篇 理学
    • 3 篇 物理学
    • 1 篇 地球物理学
  • 1 篇 医学
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 15 篇 deep denoising a...
  • 4 篇 speech enhanceme...
  • 3 篇 deep neural netw...
  • 2 篇 acoustic modelin...
  • 2 篇 noise reduction
  • 2 篇 deep learning
  • 2 篇 speech recogniti...
  • 2 篇 hearing aids
  • 2 篇 unsupervised ada...
  • 2 篇 bayes risk minim...
  • 1 篇 multiple
  • 1 篇 covid-19
  • 1 篇 speech dereverbe...
  • 1 篇 degradation of p...
  • 1 篇 class imbalance ...
  • 1 篇 imaging
  • 1 篇 short-time objec...
  • 1 篇 pneumonia
  • 1 篇 ensemble learnin...
  • 1 篇 reverberation

机构

  • 1 篇 univ macau minis...
  • 1 篇 univ calif san d...
  • 1 篇 department of el...
  • 1 篇 chung yuan chris...
  • 1 篇 natl taiwan univ...
  • 1 篇 department of el...
  • 1 篇 nhk japan broadc...
  • 1 篇 korea univ dept ...
  • 1 篇 northwestern pol...
  • 1 篇 natl inst inform...
  • 1 篇 acad sinica sti ...
  • 1 篇 shaanxi normal u...
  • 1 篇 zhejiang univ sc...
  • 1 篇 acad sinica res ...
  • 1 篇 engineering and ...
  • 1 篇 acad sinica taiw...
  • 1 篇 natl yang ming u...
  • 1 篇 natl taiwan univ...
  • 1 篇 univ belgrade sc...
  • 1 篇 sapienza univ ro...

作者

  • 2 篇 tsao yu
  • 1 篇 chiluveru samba ...
  • 1 篇 kazuo onoe
  • 1 篇 kim su min
  • 1 篇 hussain tassadaq
  • 1 篇 niu sheng-yong
  • 1 篇 grozdic dorde t.
  • 1 篇 lu xugang
  • 1 篇 he ai
  • 1 篇 wu xiaojun
  • 1 篇 li yue
  • 1 篇 zhang zhiming
  • 1 篇 tripathy manoj
  • 1 篇 guo lun-zhang
  • 1 篇 lai ying-hui
  • 1 篇 sato shoei
  • 1 篇 kobayashi akio
  • 1 篇 hegde rajesh m.
  • 1 篇 baccarelli enzo
  • 1 篇 piazzo lorenzo

语言

  • 14 篇 英文
  • 1 篇 其他
检索条件"主题词=deep denoising autoencoder"
15 条 记 录,以下是11-20 订阅
排序:
Keyword Spotting in Continuous Speech Using Spectral and Prosodic Information Fusion
收藏 引用
CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2019年 第6期38卷 2767-2791页
作者: Pandey, Laxmi Hegde, Rajesh M. Indian Inst Technol Kanpur Dept Elect Engn Kanpur Uttar Pradesh India
Keyword spotting in a continuous speech is a challenging problem and has relevance in applications like audio indexing and music retrieval. In this work, the problem of keyword spotting is addressed by utilizing the c... 详细信息
来源: 评论
Multi-objective learning based speech enhancement method to increase speech quality and intelligibility for hearing aid device users
收藏 引用
BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2019年 第0期48卷 35-45页
作者: Lai, Ying-Hui Zheng, Wei-Zhong Natl Yang Ming Univ Dept Biomed Engn Taipei Taiwan
Background noise is a critical issue for hearing aid device users;a common solution to address this problem is speech enhancement (SE). In recent times, a novel SE approach based on deep learning technology, called de... 详细信息
来源: 评论
Speech Dereverberation Based on Integrated deep and Ensemble Learning Algorithm
Speech Dereverberation Based on Integrated Deep and Ensemble...
收藏 引用
IEEE International Conference on Acoustics, Speech and Signal Processing
作者: Wei-Jen Lee Syu-Siang Wang Fei Chen Xugang Lu Shao-Yi Chien Yu Tsao Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical and Electronic Engineering Southern University of Science and Technology China National Institute of Information and Communications Technology Japan Department of Electrical Engineering National Taiwan University Taiwan
Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradation of acoustic applications. Due to a complicated combination of attenuation an... 详细信息
来源: 评论
COMPARISON OF UNSUPERVISED SEQUENCE ADAPTATIONS FOR deep NEURAL NETWORKS  41
COMPARISON OF UNSUPERVISED SEQUENCE ADAPTATIONS FOR DEEP NEU...
收藏 引用
41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
作者: Kobayashi, Akio Onoe, Kazuo Ichiki, Manon Sato, Shoei NHK Engn Syst Inc Tokyo Japan NHK Japan Broadcasting Coporat Sci & Technol Res Labs Tokyo Japan
This paper compares unsupervised sequence training techniques for deep neural networks (DNN) for broadcast transcriptions. Recent progress in digital archiving of broadcast content has made it easier to access large a... 详细信息
来源: 评论
COMPARISON OF UNSUPERVISED SEQUENCE ADAPTATIONS FOR deep NEURAL NETWORKS
COMPARISON OF UNSUPERVISED SEQUENCE ADAPTATIONS FOR DEEP NEU...
收藏 引用
IEEE International Conference on Acoustics, Speech and Signal Processing
作者: Akio Kobayashi Kazuo Onoe Manon Ichiki Shoei Sato NHK Engineering System. Inc. Tokyo Japan NHK (Japan Broadcasting Coporation) Science and Technology Research Laboratories Tokyo Japan
This paper compares unsupervised sequence training techniques for deep neural networks (DNN) for broadcast transcriptions. Recent progress in digital archiving of broadcast content has made it easier to access large a... 详细信息
来源: 评论