Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens

被引：0
|
作者：
San, Nay [1 ]
Paraskevopoulos, Georgios [2 ]
Arora, Aryaman [1 ]
He, Xiluo [1 ]
Kaur, Prabhjot [3 ]
Adams, Oliver [4 ]
Jurafsky, Dan [1 ]
机构：
[1] Stanford University, United States
[2] Athena Research Center, Greece
[3] Wayne State University, United States
[4] Atos zData
来源：
arXiv |
关键词：
Engineering Village;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Automatic speech recognition - Bengalis - Down-stream - Low-resource speech recognition - Performance - Pre-training - Speech models - Speech recognition performance - Target language - Training data
引用
收藏
相关论文
共 50 条
  • [21] ON SCALING CONTRASTIVE REPRESENTATIONS FOR LOW-RESOURCE SPEECH RECOGNITION
    Borgholt, Lasse
    Tax, Tycho M. S.
    Havtorn, Jakob D.
    Maaloe, Lars
    Igel, Christian
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 3885 - 3889
  • [22] Transfer Learning from Multi-Lingual Speech Translation Benefits Low-Resource Speech Recognition
    Vanderreydt, Geoffroy
    Remy, Francois
    Demuynck, Kris
    INTERSPEECH 2022, 2022, : 3053 - 3057
  • [23] Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition
    Zheng, Guolin
    Xiao, Yubei
    Gong, Ke
    Zhou, Pan
    Liang, Xiaodan
    Lin, Liang
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 2765 - 2777
  • [24] Robust Speech Recognition using Meta-learning for Low-resource Accents
    Eledath, Dhanya
    Baby, Arun
    Singh, Shatrughan
    2024 NATIONAL CONFERENCE ON COMMUNICATIONS, NCC, 2024,
  • [25] Using Large Self-Supervised Models for Low-Resource Speech Recognition
    Krishna, D. N.
    Wang, Pinyi
    Bozza, Bruno
    INTERSPEECH 2021, 2021, : 2436 - 2440
  • [26] Systems for Low-Resource Speech Recognition Tasks in Open Automatic Speech Recognition and Formosa Speech Recognition Challenges
    Lin, Hung-Pang
    Zhang, Yu-Jia
    Chen, Chia-Ping
    INTERSPEECH 2021, 2021, : 4339 - 4343
  • [27] Convolutional Maxout Neural Networks for Low-Resource Speech Recognition
    Cai, Meng
    Shi, Yongzhe
    Kang, Jian
    Liu, Jia
    Su, Tengrong
    2014 9TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2014, : 133 - +
  • [28] MIXSPEECH: DATA AUGMENTATION FOR LOW-RESOURCE AUTOMATIC SPEECH RECOGNITION
    Meng, Linghui
    Xu, Jin
    Tan, Xu
    Wang, Jindong
    Qin, Tao
    Xu, Bo
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 7008 - 7012
  • [29] Language fusion via adapters for low-resource speech recognition
    Hu, Qing
    Zhang, Yan
    Zhang, Xianlei
    Han, Zongyu
    Liang, Xiuxia
    SPEECH COMMUNICATION, 2024, 158
  • [30] Weighted Gradient Pretrain for Low-Resource Speech Emotion Recognition
    Xie, Yue
    Liang, Ruiyu
    Zhao, Xiaoyan
    Liang, Zhenlin
    Du, Jing
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2022, E105D (07) : 1352 - 1355
12345