Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR

被引：0
|
作者：
Maekaku, Takashi [1 ]
Fujita, Yuya [1 ]
Peng, Yifan [2 ]
Watanabe, Shinji [2 ]
机构：
[1] Yahoo Japan Corporation, Tokyo, Japan
[2] Carnegie Mellon University, PA, United States
来源：
Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH | 2022年 / 2022-September卷
关键词：
751.5; Speech;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
29
引用
下载
收藏
页码：1071 / 1075
相关论文
共 50 条
  • [1] Attention Weight Smoothing Using Prior Distributions for Transformer-Based End-to-End ASR
    Maekaku, Takashi
    Fujita, Yuya
    Peng, Yifan
    Watanabe, Shinji
    INTERSPEECH 2022, 2022, : 1071 - 1075
  • [2] TRANSFORMER-BASED END-TO-END SPEECH RECOGNITION WITH LOCAL DENSE SYNTHESIZER ATTENTION
    Xu, Menglong
    Li, Shengqiang
    Zhang, Xiao-Lei
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5899 - 5903
  • [3] TRANSFORMER-BASED ONLINE CTC/ATTENTION END-TO-END SPEECH RECOGNITION ARCHITECTURE
    Miao, Haoran
    Cheng, Gaofeng
    Gao, Changfeng
    Zhang, Pengyuan
    Yan, Yonghong
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 6084 - 6088
  • [4] Transformer-based end-to-end attack on text CAPTCHAs with triplet deep attention
    Zhang, Bo
    Xiong, Yu-Jie
    Xia, Chunming
    Gao, Yongbin
    COMPUTERS & SECURITY, 2024, 146
  • [5] SIMPLIFIED SELF-ATTENTION FOR TRANSFORMER-BASED END-TO-END SPEECH RECOGNITION
    Luo, Haoneng
    Zhang, Shiliang
    Lei, Ming
    Xie, Lei
    2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 75 - 81
  • [6] SymFormer: End-to-End Symbolic Regression Using Transformer-Based Architecture
    Vastl, Martin
    Kulhanek, Jonas
    Kubalik, Jiri
    Derner, Erik
    Babuska, Robert
    IEEE ACCESS, 2024, 12 : 37840 - 37849
  • [7] Transformer-based end-to-end scene text recognition
    Zhu, Xinghao
    Zhang, Zhi
    PROCEEDINGS OF THE 2021 IEEE 16TH CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA 2021), 2021, : 1691 - 1695
  • [8] Improving Streaming End-to-End ASR on Transformer-based Causal Models with Encoder States Revision Strategies
    Li, Zehan
    Miao, Haoran
    Deng, Keqi
    Cheng, Gaofeng
    Tian, Sanli
    Li, Ta
    Yan, Yonghong
    INTERSPEECH 2022, 2022, : 1671 - 1675
  • [9] AN END-TO-END SPEECH ACCENT RECOGNITION METHOD BASED ON HYBRID CTC/ATTENTION TRANSFORMER ASR
    Gao, Qiang
    Wu, Haiwei
    Sun, Yanqing
    Duan, Yitao
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 7253 - 7257
  • [10] Hierarchical transformer-based large-context end-to-end ASR with large-context knowledge distillation
    Masumura, Ryo
    Makishima, Naoki
    Ihori, Mana
    Takashima, Akihiko
    Tanaka, Tomohiro
    Orihashi, Shota
    arXiv, 2021,
12345