In Automatic speech recognition paradigm has been shifted from statistical model (GMM-HMM) to deep neural network. Among various types of Deep neural networks architecture, CNNs have been most broadly used and considered. There are many advanced features in CNNs like weight sharing, local filters and pooling etc. An ideal pooling method is to be expected to extract only useful information and discards irrelevant details. Pooling is an important component of CNN to be highlighted. Hence, to understand and select the best pooling technique, this paper aims to provide a broad survey on different types of pooling techniques applied in CNNs architecture. This paper will also summarize the improvements of CNNs, including key properties of CNNs, architecture of CNNs.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Convolutional Neural Network for ASR


    Contributors:


    Publication date :

    2018-03-01


    Size :

    5747022 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    TRAINING OF A CONVOLUTIONAL NEURAL NETWORK

    GRIGORESCU SORIN MIHAI / TRASNEA BOGDAN / VASILCOI ANDREI | European Patent Office | 2021

    Free access

    TRAINING OF A CONVOLUTIONAL NEURAL NETWORK

    GRIGORESCU SORIN MIHAI / TRASNEA BOGDAN / VASILCOI ANDREI | European Patent Office | 2022

    Free access


    Pedestrian Detection with Deep Convolutional Neural Network

    Chen, Xiaogang / Wei, Pengxu / Ke, Wei et al. | British Library Conference Proceedings | 2015


    Phase unwrapping with the convolutional neural network

    Wang, Shuai / Chen, Bo / Wang, Jing | British Library Conference Proceedings | 2020