Mandarin-English Code-switching Speech Recognition

被引:0
|
作者
Xu, Haihua [1 ]
Van Tung Pham [1 ,2 ]
Kyaw, Zin Tun [2 ]
Lim, Zhi Hao [1 ]
Chng, Eng Siong [1 ,2 ]
Li, Haizhou [3 ]
机构
[1] Nanyang Technol Univ, Temasek Labs, Singapore, Singapore
[2] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore
[3] Natl Univ Singapore, Dept Elect & Comp Engn, Singapore, Singapore
关键词
code-switch speech recognition; phone sets; context-aware language model; TDNN;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This work presents the development of a Mandarin-English code-switching speech recognition system. We demonstrate three key novelties in our system. First, we increase our lexicon coverage to 360K words, where phone sets of different languages are maintained separately. Secondly, we used over 1000 hours of training data combining both mono-lingual and code-switch corpus to develop the acoustic model. Finally, for language modelling, we applied context-aware text normalization and word-class language model. When testing on our internal code-switch close talk microphone recording, the system achieves recognition performance that can support real applications.
引用
收藏
页码:554 / 555
页数:2
相关论文
共 50 条
  • [1] Pronunciation augmentation for Mandarin-English code-switching speech recognition
    Long, Yanhua
    Wei, Shuang
    Lian, Jie
    Li, Yijie
    EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2021, 2021 (01)
  • [2] Pronunciation augmentation for Mandarin-English code-switching speech recognition
    Yanhua Long
    Shuang Wei
    Jie Lian
    Yijie Li
    EURASIP Journal on Audio, Speech, and Music Processing, 2021
  • [3] NON-AUTOREGRESSIVE MANDARIN-ENGLISH CODE-SWITCHING SPEECH RECOGNITION
    Chuang, Shun-Po
    Chang, Heng-Jui
    Huang, Sung-Feng
    Lee, Hung-yi
    2021 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2021, : 465 - 472
  • [4] Acoustic data augmentation for Mandarin-English code-switching speech recognition
    Long, Yanhua
    Li, Yijie
    Zhang, Qiaozheng
    Wei, Shuang
    Ye, Hong
    Yang, Jichen
    APPLIED ACOUSTICS, 2020, 161
  • [5] Cyclic Transfer Learning for Mandarin-English Code-Switching Speech Recognition
    Nga, Cao Hong
    Vu, Duc-Quang
    Luong, Huong Hoang
    Huang, Chien-Lin
    Wang, Jia-Ching
    IEEE SIGNAL PROCESSING LETTERS, 2023, 30 : 1387 - 1391
  • [6] ADDRESSING ACCENT MISMATCH IN MANDARIN-ENGLISH CODE-SWITCHING SPEECH RECOGNITION
    Tan, Zhili
    Fan, Xinghua
    Zhu, Hui
    Lin, Ed
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 8259 - 8263
  • [7] On the End-to-End Solution to Mandarin-English Code-switching Speech Recognition
    Zeng, Zhiping
    Khassanov, Yerbolat
    Van Tung Pham
    Xu, Haihua
    Chng, Eng Siong
    Li, Haizhou
    INTERSPEECH 2019, 2019, : 2165 - 2169
  • [8] INVESTIGATING END-TO-END SPEECH RECOGNITION FOR MANDARIN-ENGLISH CODE-SWITCHING
    Shan, Changhao
    Weng, Chao
    Wang, Guangsen
    Su, Dan
    Luo, Min
    Yu, Dong
    Xie, Lei
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6056 - 6060
  • [9] A Mandarin-English Code-Switching Corpus
    Li, Ying
    Yu, Yue
    Fung, Pascale
    LREC 2012 - EIGHTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2012, : 2515 - 2519
  • [10] Integrating Knowledge in End-to-End Automatic Speech Recognition for Mandarin-English Code-Switching
    Li, Chia-Yu
    Ngoc Thang Vu
    PROCEEDINGS OF THE 2019 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING (IALP), 2019, : 160 - 165