Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translation

被引：0
|
作者：
Sant, Gerard [1 ]
Gállego, Gerard I. [1 ]
Alastruey, Belen [1 ]
Costa-Jussà, Marta R. [1 ]
机构：
[1] TALP Research Center, Universitat Politècnica de Catalunya, Barcelona, Spain
来源：
NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Student Research Workshop | 2022年
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Natural language processing systems
引用
收藏
页码：277 / 284
相关论文
共 3 条
  • [1] An Improved Transformer-Based Neural Machine Translation Strategy: Interacting-Head Attention
    Li, Dongxing
    Luo, Zuying
    COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2022, 2022
  • [2] Audio-visual speech translation with automatic LIP synchronization and face tracking based on 3-D head model
    Morishima, Shigeo
    Ogata, Shin
    Murai, Kazumasa
    Nakamura, Satoshi
    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2002, 2
  • [3] COMPRESSING TRANSFORMER-BASED ASR MODEL BY TASK-DRIVEN LOSS AND ATTENTION-BASED MULTI-LEVEL FEATURE DISTILLATION
    Lv, Yongjie
    Wang, Longbiao
    Ge, Meng
    Li, Sheng
    Ding, Chenchen
    Pan, Lixin
    Wang, Yuguang
    Dang, Jianwu
    Honda, Kiyoshi
    ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2022, 2022-May : 7992 - 7996
1