The XMUSPEECH System for Accented English Automatic Speech Recognition

被引：2
|
作者：
Tong, Fuchuan [1 ]
Li, Tao [2 ]
Liao, Dexin [2 ]
Xia, Shipeng [2 ]
Li, Song [1 ]
Hong, Qingyang [2 ]
Li, Lin [1 ]
机构：
[1] Xiamen Univ, Sch Elect Sci & Engn, Xiamen 361005, Peoples R China
[2] Xiamen Univ, Sch Informat, Xiamen 361005, Peoples R China
来源：
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 03期
基金：
中国国家自然科学基金;
关键词：
AESRC2020; i-vector; x-vector; multistream CNN;
D O I：
10.3390/app12031478
中图分类号：
O6 [化学];
学科分类号：
0703 ;
摘要：
In this paper, we present the XMUSPEECH systems for Track 2 of the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC2020). Track 2 is an Automatic Speech Recognition (ASR) task where the non-native English speakers have various accents, which reduces the accuracy of the ASR system. To solve this problem, we experimented with acoustic models and input features. Furthermore, we trained a TDNN-LSTM language model for lattice rescoring to obtain better results. Compared with our baseline system, we achieved relative word error rate (WER) improvements of 40.7% and 35.7% on the development set and evaluation set, respectively.
引用
收藏
页数：8
相关论文
共 50 条
  • [31] Training of Automatic Speech Recognition System on Noised Speech
    Prodeus, Arkadiy
    Kukharicheva, Kateryna
    2016 4TH INTERNATIONAL CONFERENCE ON METHODS AND SYSTEMS OF NAVIGATION AND MOTION CONTROL (MSNMC), 2016, : 221 - 223
  • [32] Automatic tone assessment for strongly accented Mandarin speech
    Pan, Fuping
    Zhao, Qingwei
    Yan, Yonghong
    2006 8TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-4, 2006, : 783 - +
  • [33] Mispronunciation Detection and Diagnosis for Mandarin Accented English Speech
    Khanal, Subash
    Soleymanpour, Mohammad
    Bozorg, Narjes
    Johnson, Michael T.
    2021 INTERNATIONAL CONFERENCE ON SPEECH TECHNOLOGY AND HUMAN-COMPUTER DIALOGUE (SPED), 2021, : 62 - 67
  • [34] AUTOMATIC EVALUATION OF ENGLISH PRONUNCIATION BASED ON SPEECH RECOGNITION TECHNIQUES
    HAMADA, H
    MIKI, S
    NAKATSU, R
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1993, E76D (03) : 352 - 359
  • [35] Improving English Pronunciation via Automatic Speech Recognition Technology
    Li, Meihui
    Han, Meiting
    Chen, Zejia
    Mo, Yiling
    Chen, Xiujuan
    Liu, Xiaobin
    2017 INTERNATIONAL SYMPOSIUM ON EDUCATIONAL TECHNOLOGY (ISET 2017), 2017, : 224 - 228
  • [36] Improving English pronunciation via automatic speech recognition technology
    Liu, Xiaobin
    Xu, Manfei
    Li, Meihui
    Han, Meiting
    Chen, Zejia
    Mo, Yiling
    Chen, Xiujuan
    Liu, Minjia
    INTERNATIONAL JOURNAL OF INNOVATION AND LEARNING, 2019, 25 (02) : 126 - 140
  • [37] Data Augmentation Improves Recognition of Foreign Accented Speech
    Fukuda, Takashi
    Fernandez, Raul
    Rosenberg, Andrew
    Thomas, Samuel
    Ramabhadran, Bhuvana
    Sorin, Alexander
    Kurata, Gakuto
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 2409 - 2413
  • [38] Computational Modelling of the Recognition of Foreign-Accented Speech
    Scharenborg, Odette
    Witteman, Marijt
    Weber, Andrea
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 882 - 885
  • [39] Accented Speech Recognition With Accent-specific Codebooks
    Prabhu, Darshan
    Jyothi, Preethi
    Ganapathy, Sriram
    Unni, Vinit
    2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2023, 2023, : 7175 - 7188
  • [40] Speech recognition sensors and artificial intelligence automatic evaluation application in English oral correction system
    Jing, Wang
    Measurement: Sensors, 2024, 32
12345