Spontaneous talking gestures using Generative Adversarial Networks

被引：13
|
作者：
Rodriguez, Igor [1 ]
Maria Martinez-Otzeta, Jose [1 ]
Irigoien, Itziar [1 ]
Lazkano, Elena [1 ]
机构：
[1] Univ Basque Country, Fac Informat, Comp Sci & Artificial Intelligence, Manuel Lardizabal 1, Donostia San Sebastian 20018, Spain
来源：
ROBOTICS AND AUTONOMOUS SYSTEMS | 2019年 / 114卷
关键词：
Social robotics; Generative learning models; Motion generation; Principal coordinate analysis; Body language expression; Generative adversarial networks;
D O I：
10.1016/j.robot.2018.11.024
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presents a talking gesture generation system based on Generative Adversarial Networks, along with an evaluation of its adequateness. The talking gesture generation system produces a sequence of joint positions of the robot's upper body which keeps in step with an uttered sentence. The suitability of the approach is demonstrated with a real robot. Besides, the motion generation method is compared with other (non-deep) generative approaches. A two-step comparison is made. On the one hand, a statistical analysis is performed over movements generated by each approach by means of Principal Coordinate Analysis. On the other hand, the robot motion adequateness is measured by calculating the end effectors' jerk, path lengths and 3D space coverage. (C) 2019 Elsevier B.V. All rights reserved.
引用
收藏
页码：57 / 65
页数：9
相关论文
共 50 条
  • [31] Radar Image Prediction Using Generative Adversarial Networks
    Han, Lei
    Fang, Liyuan
    Zhang, Wei
    Ge, Yorong
    TWELFTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2020), 2021, 11720
  • [32] Online Signature Profiling Using Generative Adversarial Networks
    Vorugunti, Chandra Sekhar
    Mukherjee, Prerana
    Pulabaigari, Viswanath
    2020 INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS & NETWORKS (COMSNETS), 2020,
  • [33] SPEECH BANDWIDTH EXTENSION USING GENERATIVE ADVERSARIAL NETWORKS
    Li, Sen
    Villette, Stephane
    Ramadas, Pravin
    Sinder, Daniel J.
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5029 - 5033
  • [34] Improving ECG Classification Using Generative Adversarial Networks
    Golany, Tomer
    Lavee, Gal
    Yarden, Shai Tejman
    Radinsky, Kira
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 13280 - 13285
  • [35] Anonymising Pathology Data using Generative Adversarial Networks
    Morrison, David
    Harris-Birtill, David
    MEDICAL IMAGING 2022: DIGITAL AND COMPUTATIONAL PATHOLOGY, 2022, 12039
  • [36] ROBUST SPEECH RECOGNITION USING GENERATIVE ADVERSARIAL NETWORKS
    Sriram, Anuroop
    Jun, Heewoo
    Gaur, Yashesh
    Satheesh, Sanjeev
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5639 - 5643
  • [37] Clustering Using Conditional Generative Adversarial Networks (cGANs)
    Ruzicka, Marek
    Dopiriak, Matus
    2023 33RD INTERNATIONAL CONFERENCE RADIOELEKTRONIKA, RADIOELEKTRONIKA, 2023,
  • [38] Monocular Depth Prediction using Generative Adversarial Networks
    Kumar, Arun C. S.
    Bhandarkar, Suchendra M.
    Prasad, Mukta
    PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 413 - 421
  • [39] Compressing PDF sets using generative adversarial networks
    Stefano Carrazza
    Juan Cruz-Martinez
    Tanjona R. Rabemananjara
    The European Physical Journal C, 2021, 81
  • [40] Restoring Raindrops Using Attentive Generative Adversarial Networks
    Yang, Hee-Deok
    APPLIED SCIENCES-BASEL, 2021, 11 (15):
12345