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
  • [41] An Empirical Study on Transformer-Based End-to-End Speech Recognition with Novel Decoder Masking
    Weng, Shi-Yan
    Chiu, Hsuan-Sheng
    Chen, Berlin
    2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 518 - 522
  • [42] Keyword Search Using Attention-Based End-to-End ASR and Frame-Synchronous Phoneme Alignments
    Yang, Runyan
    Cheng, Gaofeng
    Miao, Haoran
    Li, Ta
    Zhang, Pengyuan
    Yan, Yonghong
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 : 3202 - 3215
  • [43] IMPROVING ATTENTION-BASED END-TO-END ASR SYSTEMS WITH SEQUENCE-BASED LOSS FUNCTIONS
    Cui, Jia
    Weng, Chao
    Wang, Guangsen
    Wang, Jun
    Wang, Peidong
    Yu, Chengzhu
    Su, Dan
    Yu, Dong
    2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 353 - 360
  • [44] Rotated-DETR: an End-to-End Transformer-based Oriented Object Detector for Aerial Images
    Kim, Jinbeom
    Lee, Giljun
    Kim, Taejune
    Woo, Simon S.
    38TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, SAC 2023, 2023, : 1248 - 1255
  • [45] An efficient transformer-based surrogate model with end-to-end training strategies for automatic history matching
    Zhang, Jinding
    Kang, Jinzheng
    Zhang, Kai
    Zhang, Liming
    Liu, Piyang
    Liu, Xingyu
    Sun, Weijia
    Wang, Guangyao
    GEOENERGY SCIENCE AND ENGINEERING, 2024, 240
  • [46] End-to-end optimized image compression with competition of prior distributions
    Brummer, Benoit
    De Vleeschouwer, Christophe
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 1890 - 1894
  • [47] Cross-Attention End-to-End ASR for Two-Party Conversations
    Kim, Suyoun
    Dalmia, Siddharth
    Metze, Florian
    INTERSPEECH 2019, 2019, : 4380 - 4384
  • [48] Data Augmentation Using CycleGAN for End-to-End Children ASR
    Singh, Dipesh K.
    Amin, Preet P.
    Sailor, Hardik B.
    Patil, Hemant A.
    29TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2021), 2021, : 511 - 515
  • [49] Iterative Compression of End-to-End ASR Model using AutoML
    Mehrotra, Abhinav
    Dudziak, Lukasz
    Yeo, Jinsu
    Lee, Young-yoon
    Vipperla, Ravichander
    Abdelfattah, Mohamed S.
    Bhattacharya, Sourav
    Ishtiaq, Samin
    Ramos, Alberto Gil C. P.
    Lee, SangJeong
    Kim, Daehyun
    Lane, Nicholas D.
    INTERSPEECH 2020, 2020, : 3361 - 3365
  • [50] Auxiliary feature based adaptation of end-to-end ASR systems
    Delcroix, Marc
    Watanabe, Shinji
    Ogawa, Atsunori
    Karita, Shigeki
    Nakatani, Tomohiro
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2444 - 2448
12345