EI / SCOPUS / CSCD 收录

中文核心期刊

ZHANG Long, LI Haifeng, MA Lin, WANG Jianhua. Automatic detection and evaluation of the Erhua in Putonghua proficiency test[J]. ACTA ACUSTICA, 2014, 39(5): 639-646. DOI: 10.15949/j.cnki.0371-0025.2014.05.016
Citation: ZHANG Long, LI Haifeng, MA Lin, WANG Jianhua. Automatic detection and evaluation of the Erhua in Putonghua proficiency test[J]. ACTA ACUSTICA, 2014, 39(5): 639-646. DOI: 10.15949/j.cnki.0371-0025.2014.05.016

Automatic detection and evaluation of the Erhua in Putonghua proficiency test

More Information
  • PACS: 
  • Received Date: August 14, 2012
  • Revised Date: February 19, 2013
  • Available Online: June 27, 2022
  • An automatic detection and evaluation method of the "Erhua" (also called "r-retrofiexion" or "retroflex suffixation") in Putonghua proficiency test (PSC) is proposed. Based on the framework of the computer aided pronunciation evaluation system, this paper makes an in-depth analysis of phonologic rules and acoustic characteristic of the Erhua, solves the detection and evaluation of the Erhua as a typical classification problem. And then more representative acoustic features are selected and a variety of different classification algorithms are used. The results showed that the boosting classification and regression tree (CART) can make full use of the characteristics of the Erhua, and the classification accuracy is 92.41%. Based on the further analysis of the acoustic feature group, we found the formant, pronunciation confidence and duration are the most important clues of the Erhua, and using these clues can effectively realize the automatic detection and evaluation of the Erhua.
  • Related Articles

    [1]WANG Bei, LIU Lu, ZHANG Xiaxia, Caroline Féry. Dual-focus production and perception in Putonghua[J]. ACTA ACUSTICA, 2019, 44(1): 1-11. DOI: 10.15949/j.cnki.0371-0025.2019.01.001
    [2]HUANG Hao, WANG Jianming, Abudureyimu Halidan, Silamu Wushour. Maximum F1-score acoustic model training for automatic mispronunciation detection[J]. ACTA ACUSTICA, 2013, 38(6): 751-758. DOI: 10.15949/j.cnki.0371-0025.2013.06.010
    [3]NI Chongjia, LIU Wenju, XU Bo. The comparison and analysis between Chinese Putonghua and English stress automatic annotation[J]. ACTA ACUSTICA, 2012, 37(5): 553-560. DOI: 10.15949/j.cnki.0371-0025.2012.05.012
    [4]ZHOU Chao, HONG Hong. Detection of double pitches for Chinese Putonghua[J]. ACTA ACUSTICA, 2011, 36(2): 239-243. DOI: 10.15949/j.cnki.0371-0025.2011.02.006
    [5]ZHANG Jialu. SAMPA-SC for standard Chinese(Putonghua)[J]. ACTA ACUSTICA, 2009, 34(1): 81-86. DOI: 10.15949/j.cnki.0371-0025.2009.01.014
    [6]DONG Bin, ZHAO Qingwei, YAN Yonghong. Objective evaluation of vowels of standard Chinese pronunciation based on formant pattern[J]. ACTA ACUSTICA, 2007, 32(2): 122-128. DOI: 10.15949/j.cnki.0371-0025.2007.02.005
    [7]ZHANG Jialu. The distinctive feature trees of Standard Chinese (Putonghua)[J]. ACTA ACUSTICA, 2006, 31(3): 193-198. DOI: 10.15949/j.cnki.0371-0025.2006.03.001
    [8]ZHANG Jialu. The distinctive features for standard Chinese (Putonghua)[J]. ACTA ACUSTICA, 2005, 30(6): 506-514. DOI: 10.15949/j.cnki.0371-0025.2005.06.005
    [9]CHEN Jingjun, LU Jiren, WU Peirong. An automatic detection method of amplitude modulated broad-band signal[J]. ACTA ACUSTICA, 2004, 29(6): 544-550. DOI: 10.15949/j.cnki.0371-0025.2004.06.010
    [10]GUO Ming, CHEN Yunfeng. Password selection on automatic speaker recognition[J]. ACTA ACUSTICA, 1993, 18(2): 148-153. DOI: 10.15949/j.cnki.0371-0025.1993.02.009

Catalog

    Article Metrics

    Article views (37) PDF downloads (8) Cited by()
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return