On the use of convolutional neural networks in pairwise language recognition

被引：6
|
作者：
机构：
[1] Lozano-Diez, Alicia
[2] Gonzalez-Dominguez, Javier
[3] Zazo, Ruben
[4] Ramos, Daniel
[5] Gonzalez-Rodriguez, Joaquin
来源：
| 1600年 / Springer Verlag卷 / 8854期
关键词：
CDNNs - Convolutional networks - Fusion systems - I vectors - Language recognition - Reference systems - Total variabilities;
D O I：
10.1007/978-3-319-13623-3_9
中图分类号：
学科分类号：
摘要：
Convolutional deep neural networks (CDNNs) have been successfully applied to different tasks within the machine learning field, and, in particular, to speech, speaker and language recognition. In this work, we have applied them to pair-wise language recognition tasks. The proposed systems have been evaluated on challenging pairs of languages from NIST LRE’09 dataset. Results have been compared with two spectral systems based on Factor Analysis and Total Variability (i-vector) strategies, respectively. Moreover, a simple fusion of the developed approaches and the reference systems has been performed. Some individual and fusion systems outperform the reference systems, obtaining ∼ 17% of relative improvement in terms of minCDET for one of the challenging pairs. © Springer International Publishing Switzerland 2014.
引用
收藏
相关论文
共 50 条
  • [11] Dynamic Sign Language Recognition Based on Convolutional Neural Networks and Texture Maps
    Escobedo, Edwin
    Ramirez, Lourdes
    Camara, Guillermo
    2019 32ND SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 2019, : 265 - 272
  • [12] Recurrent Convolutional Neural Networks for Continuous Sign Language Recognition by Staged Optimization
    Cui, Runpeng
    Liu, Hu
    Zhang, Changshui
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 1610 - 1618
  • [13] Optimization of Convolutional Neural Networks Architectures Using PSO for Sign Language Recognition
    Fregoso, Jonathan
    Gonzalez, Claudia, I
    Martinez, Gabriela E.
    AXIOMS, 2021, 10 (03)
  • [14] 3D Convolutional Neural Networks for Dynamic Sign Language Recognition
    Liang, Zhi-Jie
    Liao, Sheng-Bin
    Hu, Bing-Zhang
    COMPUTER JOURNAL, 2018, 61 (11): : 1724 - 1736
  • [15] Using Convolutional Neural Networks for Fingerspelling Sign Recognition in Brazilian Sign Language
    Lima, Douglas F. L.
    Salvador Neto, Armando S.
    Santos, Ewerton N.
    Araujo, Tiago Maritan U.
    Rego, Thais Gaudencio
    WEBMEDIA 2019: PROCEEDINGS OF THE 25TH BRAZILLIAN SYMPOSIUM ON MULTIMEDIA AND THE WEB, 2019, : 109 - 115
  • [16] American Sign Language Recognition with Convolutional Neural Networks: A Gateway to Enhanced Inclusivity
    El-Marzouki, Naoufal
    Lasri, Imane
    Riadsolh, Anouar
    Elbelkacemi, Mourad
    DIGITAL TECHNOLOGIES AND APPLICATIONS, ICDTA 2024, VOL 3, 2024, 1100 : 24 - 33
  • [17] Sign Language Recognition Based on 3D Convolutional Neural Networks
    Ramos Neto, Geovane M.
    Braz Junior, Geraldo
    Sousa de Almeida, Joao Dallyson
    de Paiva, Anselmo Cardoso
    IMAGE ANALYSIS AND RECOGNITION (ICIAR 2018), 2018, 10882 : 399 - 407
  • [18] SIGN LANGUAGE RECOGNITION USING 3D CONVOLUTIONAL NEURAL NETWORKS
    Huang, Jie
    Zhou, Wengang
    Li, Houqiang
    Li, Weiping
    2015 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO (ICME), 2015,
  • [19] Convolutional Neural Networks for Phoneme Recognition
    Glackin, Cornelius
    Wall, Julie
    Chollet, Gerard
    Dugan, Nazim
    Cannings, Nigel
    PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS (ICPRAM 2018), 2018, : 190 - 195
  • [20] 3D object recognition based on pairwise Multi-view Convolutional Neural Networks
    Gao, Z.
    Wang, D. Y.
    Xue, Y. B.
    Xu, G. P.
    Zhang, H.
    Wang, Y. L.
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2018, 56 : 305 - 315
12345