Unsupervised Audio Segmentation based on Restricted Boltzmann Machines

被引:0
|
作者
Pikrakis, Aggelos [1 ]
机构
[1] Univ Piraeus, Sch Informat & Commun Technol, Dept Informat, Piraeus, Greece
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper the Conditional Restricted Boltzmann Machine (CRBM) is employed in the context of unsupervised audio segmentation. The CRBM acts as a temporal modeling method and learns, from a maximum likelihood perspective, the temporal relationships of the feature vectors that have been extracted from a large corpus of training data. After the CRBM has been trained, we quantify the correlation of the activation of the neurons of the hidden layer for successive feature vectors by means of an appropriately defined similarity function. A simple thresholding scheme is then applied on the output of the similarity function to segment automatically the audio recording. Our experiments have been carried out on a large corpus of documentaries. We provide an interpretation of the segmentation results and comment on the segmentation efficiency of the method.
引用
收藏
页码:311 / 314
页数:4
相关论文
共 50 条
  • [1] Unsupervised Rotation Factorization in Restricted Boltzmann Machines
    Giuffrida, Mario Valerio
    Tsaftaris, Sotirios A.
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 (01) : 2166 - 2175
  • [2] Unsupervised Synaptic Pruning Strategies for Restricted Boltzmann Machines
    Kalyan, Surabhi
    Joshi, Siddharth
    Sheik, Sadique
    Pedroni, Bruno U.
    Cauwenberghs, Gert
    [J]. 2018 IEEE BIOMEDICAL CIRCUITS AND SYSTEMS CONFERENCE (BIOCAS): ADVANCED SYSTEMS FOR ENHANCING HUMAN HEALTH, 2018, : 447 - 450
  • [3] Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines
    Goh, Hanlin
    Thome, Nicolas
    Cord, Matthieu
    Lim, Joo-Hwee
    [J]. COMPUTER VISION - ECCV 2012, PT V, 2012, 7576 : 298 - 311
  • [4] Mode-assisted unsupervised learning of restricted Boltzmann machines
    Haik Manukian
    Yan Ru Pei
    Sean R. B. Bearden
    Massimiliano Di Ventra
    [J]. Communications Physics, 3
  • [5] Mode-assisted unsupervised learning of restricted Boltzmann machines
    Manukian, Haik
    Pei, Yan Ru
    Bearden, Sean R. B.
    Di Ventra, Massimiliano
    [J]. COMMUNICATIONS PHYSICS, 2020, 3 (01)
  • [6] Deterministic and Generalized Framework for Unsupervised Learning with Restricted Boltzmann Machines
    Tramel, Eric W.
    Gabrie, Marylou
    Manoel, Andre
    Caltagirone, Francesco
    Krzakala, Florent
    [J]. PHYSICAL REVIEW X, 2018, 8 (04):
  • [7] Research on unsupervised feature learning for Android malware detection based on Restricted Boltzmann Machines
    Liu, Zhen
    Wang, Ruoyu
    Japkowicz, Nathalie
    Tang, Deyu
    Zhang, Wenbin
    Zhao, Jie
    [J]. Wang, Ruoyu (rywang@scut.edu.cn), 1600, Elsevier B.V. (120): : 91 - 108
  • [8] Research on unsupervised feature learning for Android malware detection based on Restricted Boltzmann Machines
    Liu, Zhen
    Wang, Ruoyu
    Japkowicz, Nathalie
    Tang, Deyu
    Zhang, Wenbin
    Zhao, Jie
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2021, 120 : 91 - 108
  • [9] Temperature based Restricted Boltzmann Machines
    Guoqi Li
    Lei Deng
    Yi Xu
    Changyun Wen
    Wei Wang
    Jing Pei
    Luping Shi
    [J]. Scientific Reports, 6
  • [10] Temperature based Restricted Boltzmann Machines
    Li, Guoqi
    Deng, Lei
    Xu, Yi
    Wen, Changyun
    Wang, Wei
    Pei, Jing
    Shi, Luping
    [J]. SCIENTIFIC REPORTS, 2016, 6