| Peer-Reviewed

Research on Automatic Speech Analysis for Teacher’s Q&A in Classroom

Received: 20 April 2017     Published: 20 April 2017
Views:       Downloads:
Abstract

Question-and-aswer (Q&A) is the important content of classroom evaluation. In order to meet the needs of large-scale class evaluation, this work uses voice analysis technology to implement exploratory research on automatic Q&A analyse, mainly on speaker recognition based on MFCC Gaussian mixture model and closed/open question identification based on the logistic regression method. The Q&A auto-analysis system developed in this work can perform automatic analyses for several classroom evaluation indexes including Q&A times, speaking durations of the teacher and his students, and the number of open questions and closed questions. For the real classroom teaching video down-loaded from “CCTV network Chinese public class”, both the speaker recognition and closed/open questions identification of this work have obtained satisfied recognition accuracy with recognition rates above 93%.

Published in Science Innovation (Volume 5, Issue 3)
DOI 10.11648/j.si.20170503.14
Page(s) 144-150
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2017. Published by Science Publishing Group

Keywords

Classroom Evaluation, Interaction Among a Teacher and Students, Logistic Regression Model, Speaker Recognition

References
[1] 钟启泉.课堂评价的挑战[J].全球教育展望,2012,(01):10-16。
[2] 崔允漷.论课堂观察LICC范式:一种专业的听评课[J].教育研究,2012,(05):79-83。
[3] 郭绍青,张绒,马彦龙.“有效教学”课堂录像分析方法与工具研究[J].电化教育研究,2013,(01):68-72。
[4] 时丽莉.“弗兰德互动分析系统”在课堂教学中的应用[J].首都师范大学学报(社会科学版),2004,(S2):163-165。
[5] 方海光,高辰柱,陈佳.改进型弗兰德斯互动分析系统及其应用[J].中国电化教育,2012,(10):109-113。
[6] 顾小清,王炜.支持教师专业发展的课堂分析技术新探索[J].中国电化教育,2004,(07):18-21。
[7] Lu Z, Liu B, Shen L. Speech endpoint detection in strong noisy environment based on the Hilbert-Huang Transform [C]// International Conference on Mechatronics and Automation. IEEE, 2009: 4322-4326.
[8] 宋知用.MATLAB在语音信号分析与合成中的应用[M].北京航空航天大学出版社,2013:116-154。
[9] 熊华乔,郑建彬等.基于说话人模型聚类的说话人识别[J].计算机工程与应用.2014,50(02):133-137。
[10] Zufeng Weng. Lin Li. Donghui Guo. Speaker Recognition Using Weighted Dynamic MFCC Based on GMM [C]. Anti-Counterfeiting Security and Identification in Communication (ASID), 2010(07):18-20.
[11] 胡政权,曾毓敏,宗原,等.说话人识别中MFCC参数提取的改进[J].计算机工程与应用.2014,50(07):217-220。
[12] Xinxing Ling. Ling Zhan. Hong Zhao. Ping Zhou. Speaker Recognition System Using the Improved GMM-based Clustering Algorithm [C]. Intelligent Computing and Integrated Systems (ICISS), 2010(10):22-24.
[13] 赵力.语音信号处理[M].机械工业出版社,2016:228-230。
[14] 叶立军,周芳丽.基于录像分析背景下的教师提问方式研究[J].教育理论与实践,2012,(05):52-54。
[15] 黄伟.提问与对话:有效教学的入口与路径[M].浙江大学出版社,2016:73-92。
[16] PeterHarrington,李锐等.机器学习实战[M].人民邮电出版社,2013:73-88。
[17] Thomson R P. Strategies for effective teaching.[J]. Nln Publ, 1975(16-1538):12-24.
Cite This Article
  • APA Style

    Wenquan Chang, Dongxing Li, Zuying Luo. (2017). Research on Automatic Speech Analysis for Teacher’s Q&A in Classroom. Science Innovation, 5(3), 144-150. https://doi.org/10.11648/j.si.20170503.14

    Copy | Download

    ACS Style

    Wenquan Chang; Dongxing Li; Zuying Luo. Research on Automatic Speech Analysis for Teacher’s Q&A in Classroom. Sci. Innov. 2017, 5(3), 144-150. doi: 10.11648/j.si.20170503.14

    Copy | Download

    AMA Style

    Wenquan Chang, Dongxing Li, Zuying Luo. Research on Automatic Speech Analysis for Teacher’s Q&A in Classroom. Sci Innov. 2017;5(3):144-150. doi: 10.11648/j.si.20170503.14

    Copy | Download

  • @article{10.11648/j.si.20170503.14,
      author = {Wenquan Chang and Dongxing Li and Zuying Luo},
      title = {Research on Automatic Speech Analysis for Teacher’s Q&A in Classroom},
      journal = {Science Innovation},
      volume = {5},
      number = {3},
      pages = {144-150},
      doi = {10.11648/j.si.20170503.14},
      url = {https://doi.org/10.11648/j.si.20170503.14},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.si.20170503.14},
      abstract = {Question-and-aswer (Q&A) is the important content of classroom evaluation. In order to meet the needs of large-scale class evaluation, this work uses voice analysis technology to implement exploratory research on automatic Q&A analyse, mainly on speaker recognition based on MFCC Gaussian mixture model and closed/open question identification based on the logistic regression method. The Q&A auto-analysis system developed in this work can perform automatic analyses for several classroom evaluation indexes including Q&A times, speaking durations of the teacher and his students, and the number of open questions and closed questions. For the real classroom teaching video down-loaded from “CCTV network Chinese public class”, both the speaker recognition and closed/open questions identification of this work have obtained satisfied recognition accuracy with recognition rates above 93%.},
     year = {2017}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Research on Automatic Speech Analysis for Teacher’s Q&A in Classroom
    AU  - Wenquan Chang
    AU  - Dongxing Li
    AU  - Zuying Luo
    Y1  - 2017/04/20
    PY  - 2017
    N1  - https://doi.org/10.11648/j.si.20170503.14
    DO  - 10.11648/j.si.20170503.14
    T2  - Science Innovation
    JF  - Science Innovation
    JO  - Science Innovation
    SP  - 144
    EP  - 150
    PB  - Science Publishing Group
    SN  - 2328-787X
    UR  - https://doi.org/10.11648/j.si.20170503.14
    AB  - Question-and-aswer (Q&A) is the important content of classroom evaluation. In order to meet the needs of large-scale class evaluation, this work uses voice analysis technology to implement exploratory research on automatic Q&A analyse, mainly on speaker recognition based on MFCC Gaussian mixture model and closed/open question identification based on the logistic regression method. The Q&A auto-analysis system developed in this work can perform automatic analyses for several classroom evaluation indexes including Q&A times, speaking durations of the teacher and his students, and the number of open questions and closed questions. For the real classroom teaching video down-loaded from “CCTV network Chinese public class”, both the speaker recognition and closed/open questions identification of this work have obtained satisfied recognition accuracy with recognition rates above 93%.
    VL  - 5
    IS  - 3
    ER  - 

    Copy | Download

Author Information
  • College of Information Science and Technology, Beijing Normal University, Beijing, China

  • College of Information Science and Technology, Beijing Normal University, Beijing, China

  • College of Information Science and Technology, Beijing Normal University, Beijing, China

  • Sections