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
  • [1] Multilingual acoustic models for speech recognition in low-resource devices
    Garcia, Enrique Gil
    Mengusoglu, Erhan
    Janke, Eric
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 981 - +
  • [2] Acoustic Modeling for Hindi Speech Recognition in Low-Resource Settings
    Dey, Anik
    Zhang, Weibin
    Fung, Pascale
    2014 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING (ICALIP), VOLS 1-2, 2014, : 891 - 894
  • [3] Acoustic model training using self-attention for low-resource speech recognition
    Park, Hosung
    Kim, Ji-Hwan
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2020, 39 (05): : 483 - 489
  • [4] Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training
    Biswas, Astik
    Menon, Raghav
    van der Westhuizen, Ewald
    Niesler, Thomas
    INTERSPEECH 2019, 2019, : 3008 - 3012
  • [5] Multilingual Meta-Transfer Learning for Low-Resource Speech Recognition
    Zhou, Rui
    Koshikawa, Takaki
    Ito, Akinori
    Nose, Takashi
    Chen, Chia-Ping
    IEEE ACCESS, 2024, 12 : 158493 - 158504
  • [6] Language-Adversarial Transfer Learning for Low-Resource Speech Recognition
    Yi, Jiangyan
    Tao, Jianhua
    Wen, Zhengqi
    Bai, Ye
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2019, 27 (03) : 621 - 630
  • [7] Low-resource Sinhala Speech Recognition using Deep Learning
    Karunathilaka, Hirunika
    Welgama, Viraj
    Nadungodage, Thilini
    Weerasinghe, Ruvan
    2020 20TH INTERNATIONAL CONFERENCE ON ADVANCES IN ICT FOR EMERGING REGIONS (ICTER-2020), 2020, : 196 - 201
  • [8] Acoustic Modeling Based on Deep Learning for Low-Resource Speech Recognition: An Overview
    Yu, Chongchong
    Kang, Meng
    Chen, Yunbing
    Wu, Jiajia
    Zhao, Xia
    IEEE ACCESS, 2020, 8 : 163829 - 163843
  • [9] Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-Resource Speech Recognition
    Yi, Cheng
    Zhou, Shiyu
    Xu, Bo
    IEEE SIGNAL PROCESSING LETTERS, 2021, 28 (28) : 788 - 792
  • [10] CURRICULUM OPTIMIZATION FOR LOW-RESOURCE SPEECH RECOGNITION
    Kuznetsova, Anastasia
    Kumar, Anurag
    Fox, Jennifer Drexler
    Tyers, Francis M.
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 8187 - 8191
12345